© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73499
    Prev
    Next
    INDEX
    Explanations

    HTML links and biological terms

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

    numerical formatting in technical documents, particularly when displaying numbers, code, or measurements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron primarily fires on tokens containing digits (i.e. numeric values or identifiers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reſ
    -0.90
     Diſ
    -0.88
     principally
    -0.87
    ալ
    -0.83
     all
    -0.81
    cnpj
    -0.81
     Presiding
    -0.80
    "}";
    -0.79
    นาย
    -0.79
    kimono
    -0.77
    POSITIVE LOGITS
     vaak
    1.02
    often
    0.95
    ^{\
    0.94
    是怎么回事
    0.94
    峦
    0.92
     poate
    0.91
    $^{\
    0.90
     seu
    0.88
    作战
    0.88
     FOLLOWING
    0.87
    Activations Density 0.063%

    No Known Activations