© 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. 56754
    Prev
    Next
    INDEX
    Explanations

    font awesome classes

    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
    ＊＊
    -0.75
     Motos
    -0.74
     alip
    -0.72
    內容簡介
    -0.71
    ounen
    -0.71
    FromNib
    -0.71
     Sinal
    -0.70
     spett
    -0.70
    徂
    -0.69
    chádz
    -0.69
    POSITIVE LOGITS
     fa
    2.41
    fa
    2.02
    fas
    1.95
     fas
    1.91
     Fa
    1.75
    Fa
    1.73
     La
    1.42
     la
    1.41
     Fas
    1.32
     FA
    1.31
    Activations Density 0.033%

    No Known Activations