© 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. 15441
    Prev
    Next
    INDEX
    Explanations

    moreover, furthermore

    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
     
    -2.39
    ↵↵↵
    -2.09
     "
    -1.71
    %;
    -1.58
     P
    -1.56
     S
    -1.55
    N
    -1.54
    </h3>
    -1.50
     N
    -1.48
     V
    -1.47
    POSITIVE LOGITS
    訁
    1.72
     太阳
    1.58
     皮肤
    1.57
     where
    1.56
     早餐
    1.50
     that
    1.44
     sorri
    1.43
     with
    1.43
     美丽
    1.43
    〮
    1.41
    Activations Density 0.045%

    No Known Activations