© 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. 62687
    Prev
    Next
    INDEX
    Explanations

    technical or specific terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
     духовке
    -0.80
    logne
    -0.79
    ның
    -0.77
    bringer
    -0.76
    setters
    -0.75
     tenor
    -0.75
    entrant
    -0.75
    官
    -0.74
    灸
    -0.73
    褐
    -0.71
    POSITIVE LOGITS
    Although
    1.11
     of
    1.02
     Although
    0.94
     unserer
    0.91
    ůl
    0.91
     although
    0.88
    wah
    0.83
    iplin
    0.83
    although
    0.83
     {
    0.80
    Activations Density 0.001%

    No Known Activations