© 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. 21196
    Prev
    Next
    INDEX
    Explanations

    messy or disordered

    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
    ”),
    -1.98
     navig
    -1.94
    ");
    -1.82
    ｐ
    -1.81
    ｏ
    -1.78
    </td>
    -1.77
     name
    -1.73
    indelijk
    -1.72
    ")
    -1.70
    (
    -1.68
    POSITIVE LOGITS
    遢
    2.19
    time
    1.97
    TryDecode
    1.88
     Etching
    1.84
    なども
    1.81
     keempat
    1.79
     husky
    1.79
     również
    1.74
     haughty
    1.74
     будем
    1.70
    Activations Density 0.003%

    No Known Activations