© 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. 56938
    Prev
    Next
    INDEX
    Explanations

    click here

    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
    SBS
    -0.85
    Residual
    -0.77
    Amino
    -0.75
    zość
    -0.74
    Genus
    -0.73
    ই
    -0.72
    FormsModule
    -0.71
    Radar
    -0.71
     Ola
    -0.71
     intern
    -0.71
    POSITIVE LOGITS
     click
    1.36
    click
    1.05
    resources
    1.00
     resources
    0.97
     continued
    0.94
     clicking
    0.92
    Click
    0.92
     homepage
    0.91
     Click
    0.91
     redirected
    0.90
    Activations Density 0.021%

    No Known Activations