© 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. 10-GEMMASCOPE-RES-131K
    7. 58849
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and symbols

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

    LaTeX formatting code for mathematical notation, particularly the '\rm' command for Roman font style.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    <bos>
    -2.52
    1
    -2.16
    ꦢ
    -2.14
    できない
    -2.06
    ⃢
    -1.99
    𝄆
    -1.97
    ⛦
    -1.95
     fotógrafo
    -1.85
     capacité
    -1.84
    鐐
    -1.83
    POSITIVE LOGITS
    {
    2.66
    чении
    1.98
    𝗽
    1.87
     Careful
    1.82
    zień
    1.80
     Important
    1.80
     Because
    1.80
    %";
    1.79
    躋
    1.78
     Personally
    1.77
    Activations Density 0.002%

    No Known Activations