© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5368
    Prev
    Next
    INDEX
    Explanations

    - "**Setting:** A quiet corner..." - "**Target Audience:** 2nd-year Physics students..." - "**Yields:** About 2-3 large jars..." - "**Recipe: Beef & Veggie Scramble with Cucumber Salad** **Yields:** 2 Servings..." - "**Lesson Plan: Introduction to Political Science - Power, Systems, & Ideologies** **Subject:** Political Science..." - "**Scene: The Clockwork Cell** **Setting:** A circular cell..." - "**Title:** Skybound Sisters..."The

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on document metadata labels or field names (e.g. “Prerequisite,” “Power Source,” “Hours Of Operation,” “Humidity,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '!
    0.54
    !',
    0.53
    !”,
    0.52
    "!
    0.50
    !,
    0.50
     (!)
    0.50
     問
    0.49
     pierwszy
    0.49
     යන
    0.48
    おはよう
    0.48
    POSITIVE LOGITS
    :
    1.20
    ：
    1.19
    :[
    1.02
    ：《
    1.00
     :
    1.00
    ﹕
    0.96
    :@
    0.90
    ："
    0.88
    ：（
    0.87
    ︰
    0.87
    Activations Density 0.033%

    No Known Activations