© 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. 32922
    Prev
    Next
    INDEX
    Explanations

    story continued below

    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
     frenos
    -1.01
     annonce
    -0.99
    hubung
    -0.96
    rozum
    -0.94
     หนัง
    -0.94
    château
    -0.94
     reprezent
    -0.93
    streamer
    -0.92
    esian
    -0.92
     Pense
    -0.91
    POSITIVE LOGITS
     with
    1.12
     starker
    0.93
    外部
    0.87
     ͡°)
    0.84
    ci
    0.84
    려
    0.82
     remained
    0.82
     Sarasota
    0.80
     Helfer
    0.80
     became
    0.79
    Activations Density 0.005%

    No Known Activations