© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 395
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on named‐entity tokens (e.g. people’s names, place names, organization names, book/chapter references, dates, 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_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
    र्यंत
    0.63
     보인다
    0.61
    \/}
    0.60
    린다
    0.59
    ॑
    0.59
     रक्षाबंधनाच्या
    0.58
     प्रकल्
    0.57
    다라고
    0.57
     पाण्याच्या
    0.56
    ôts
    0.55
    POSITIVE LOGITS
    ;
    3.17
    ;
    2.53
    ();
    2.50
     ;
    2.42
    ;//
    2.42
    ؛
    2.38
    .;
    2.34
    !;
    2.30
    );
    2.25
    ;}
    2.22
    Activations Density 0.344%

    No Known Activations