© 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. 71488
    Prev
    Next
    INDEX
    Explanations

    Joshua Names

    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
    
    -3.20
    ஂ
    -3.05
    t
    -2.89
    Ꮉ
    -2.89
    e
    -2.77
    u
    -2.70
    漼
    -2.69
    i
    -2.66
    m
    -2.59
    K
    -2.53
    POSITIVE LOGITS
    会
    2.44
    狁
    2.34
     Ausdrücke
    2.27
    ’
    2.23
     Of
    2.13
    isição
    2.13
    ,“
    2.11
     gebeten
    2.09
    ות
    2.08
    蹰
    2.06
    Activations Density 0.004%

    No Known Activations