© 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. 7955
    Prev
    Next
    INDEX
    Explanations

    an followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    to
    -2.77
    鹮
    -2.55
     彼女
    -2.45
     แต่
    -2.42
    螓
    -2.36
    ሯ
    -2.36
     klarer
    -2.20
     imitating
    -2.19
    ㈬
    -2.17
     municípios
    -2.16
    POSITIVE LOGITS
    </b>
    2.69
    \
    2.61
    __))
    2.61
    н
    2.58
    紧接着
    2.56
     Коли
    2.42
    本來
    2.36
    ");
    2.25
    An
    2.22
    <
    2.19
    Activations Density 0.022%

    No Known Activations