© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12624
    Prev
    Next
    INDEX
    Explanations

    import statements for libraries

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

    This neuron detects formal legal or policy language—words and phrases typical of disclaimers, patent filings, terms-of-service, and similar regulatory or compliance contexts.

    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
     ();
    0.74
    );
    0.65
     []);
    0.65
    !;
    0.65
    .);
    0.64
    ?;
    0.63
     [];
    0.63
     .;
    0.63
    !);
    0.63
    ();
    0.61
    POSITIVE LOGITS
     digitally
    0.59
     digitalization
    0.58
    digital
    0.56
    음을
    0.56
    饽
    0.56
     digitization
    0.55
    数字化
    0.54
    "*
    0.54
     l
    0.54
    gil
    0.54
    Activations Density 0.000%

    No Known Activations