© 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. 29994
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation

    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
    Negative Logits
    compared
    -0.91
    celot
    -0.77
    REMOV
    -0.75
     Ис
    -0.75
    considering
    -0.75
    ارو
    -0.73
    薨
    -0.73
    buff
    -0.73
    entyfik
    -0.73
     thor
    -0.73
    POSITIVE LOGITS
     good
    0.85
    安全性
    0.82
     because
    0.82
     cannot
    0.81
     manner
    0.79
    ाल
    0.75
     also
    0.73
    checkNotNull
    0.71
     hogyan
    0.70
     maintains
    0.70
    Activations Density 0.037%

    No Known Activations