© 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. 22-GEMMASCOPE-RES-131K
    7. 127964
    Prev
    Next
    INDEX
    Explanations

    iterating over collections

    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_22/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
    NSFW
    -0.95
     dugaan
    -0.86
    イクアウト
    -0.85
    elen
    -0.84
     velha
    -0.83
    lerinden
    -0.82
    athon
    -0.82
     referirse
    -0.82
    alogical
    -0.81
    atorio
    -0.81
    POSITIVE LOGITS
     then
    1.17
     каждого
    0.95
    Then
    0.93
    每個
    0.91
    每一个
    0.88
    ᐈ
    0.86
    katan
    0.85
     each
    0.85
     einzeln
    0.85
    astă
    0.84
    Activations Density 0.017%

    No Known Activations