© 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. 4237
    Prev
    Next
    INDEX
    Explanations

    names and places

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

    This neuron activates on capitalized tokens—i.e. proper nouns or named entities (names, titles, organizations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to proper nouns, particularly names of people, places, and organizations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to proper nouns and honorific titles, especially names of people, places, and formal entities.

    oai_token-act-pair · gpt-5Triggered 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
    -
    0.43
    N
    0.41
    F
    0.40
    es
    0.39
     (
    0.39
     tại
    0.39
    ,
    0.39
    У
    0.38
    ส
    0.37
    น
    0.37
    POSITIVE LOGITS
     demasi
    0.45
     penchant
    0.45
     sienten
    0.44
    いろんな
    0.43
    व्यक्तित्व
    0.43
    pengaruhi
    0.43
     배워
    0.42
     rupani
    0.42
    覷
    0.42
     badass
    0.42
    Activations Density 0.000%

    No Known Activations