© 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. 13950
    Prev
    Next
    INDEX
    Explanations

    counties and towns

    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
    ,
    -1.41
    所以我
    -1.36
     prisonniers
    -1.34
     вместо
    -1.27
    因此
    -1.26
     réfugiés
    -1.26
    er
    -1.22
     misde
    -1.21
    сль
    -1.21
    ┍
    -1.20
    POSITIVE LOGITS
    ";
    1.97
    {
    1.92
    </i>
    1.85
    >";
    1.70
     {
    1.68
    )";
    1.64
    ⫹
    1.55
     για
    1.54
    >>;
    1.52
    </sub>
    1.52
    Activations Density 0.062%

    No Known Activations