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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8275
    Prev
    Next
    INDEX
    Explanations

    black hole mass

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

    The neuron fires strongly on wire-service attribution labels (e.g. “(BUSINESS WIRE)”).

    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_31_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
     سکتی
    0.59
     tocó
    0.59
     registró
    0.57
    ッフ
    0.56
    骤
    0.56
    酽
    0.55
     跳转
    0.55
     Representatives
    0.54
     Toute
    0.54
     Pennsylvania
    0.53
    POSITIVE LOGITS
    Black
    0.58
    (_,
    0.57
     frag
    0.54
     نفس
    0.54
    (\\
    0.53
    black
    0.52
    subs
    0.52
    绾
    0.52
    object
    0.52
    执
    0.52
    Activations Density 0.000%

    No Known Activations