© 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. 84252
    Prev
    Next
    INDEX
    Explanations

    for duration

    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
    utches
    -1.52
    Ꮉ
    -1.43
     wann
    -1.43
     kuid
    -1.39
    what
    -1.35
    up
    -1.35
    それ
    -1.35
     AFFAIRS
    -1.35
     kuni
    -1.34
     bArr
    -1.31
    POSITIVE LOGITS
     or
    1.68
    ,
    1.53
    -
    1.50
    </strong>
    1.49
     at
    1.44
    .
    1.43
     cieka
    1.35
    门口
    1.34
    er
    1.34
     mismos
    1.34
    Activations Density 0.012%

    No Known Activations