© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106440
    Prev
    Next
    INDEX
    Explanations

    connecting items or concepts

    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_34/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
    ⋄
    -0.77
    менте
    -0.74
    UserProfile
    -0.73
    ѝ
    -0.72
    ettbewer
    -0.72
     metabol
    -0.69
    fter
    -0.69
     alphabe
    -0.69
    ívne
    -0.68
     for
    -0.67
    POSITIVE LOGITS
     bogor
    0.76
     surabaya
    0.73
    وفر
    0.73
    🪕
    0.73
     Più
    0.73
    bukkit
    0.73
    drá
    0.71
    -#
    0.71
     حض
    0.70
     forthcoming
    0.70
    Activations Density 0.022%

    No Known Activations