© 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. 113136
    Prev
    Next
    INDEX
    Explanations

    hawk and jayhawk

    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
    ↵
    -3.38
    大概是
    -2.64
    就很
    -2.42
    2
    -2.41
     fastened
    -2.38
    </h3>
    -2.33
    ção
    -2.31
    ”
    -2.31
    ть
    -2.30
    真的是
    -2.28
    POSITIVE LOGITS
    蠖
    2.52
     και
    2.50
    </td>
    2.42
    蛩
    2.41
    ዡ
    2.39
    薷
    2.39
     情侣
    2.39
     changements
    2.28
     tenacity
    2.25
    
    2.25
    Activations Density 0.005%

    No Known Activations