© 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. 127867
    Prev
    Next
    INDEX
    Explanations

    campaigning

    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
    她就
    -2.13
     止
    -1.92
     перец
    -1.90
     flere
    -1.88
     {
    -1.88
     of
    -1.86
     experimenting
    -1.74
    外人
    -1.73
     $
    -1.70
     «
    -1.70
    POSITIVE LOGITS
    栳
    2.31
     hunne
    2.14
     groet
    2.05
    <td>
    1.88
     эту
    1.86
    你的
    1.86
     These
    1.84
    淠
    1.82
     theses
    1.80
     一个
    1.79
    Activations Density 0.008%

    No Known Activations