© 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. 3464
    Prev
    Next
    INDEX
    Explanations

    statistical topics and 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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     speculative
    -0.98
     speculation
    -0.90
    cheidung
    -0.82
     speculating
    -0.81
     doppio
    -0.79
    予想
    -0.77
    prepared
    -0.76
    ylon
    -0.75
    yson
    -0.75
    ὕ
    -0.75
    POSITIVE LOGITS
     statistical
    1.30
     Statistics
    1.25
    Statistical
    1.21
     Statistical
    1.21
     statisti
    1.20
     stats
    1.14
    Stats
    1.11
     statistics
    1.09
    Statistics
    1.08
     статисти
    1.08
    Activations Density 0.048%

    No Known Activations