© 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. 47205
    Prev
    Next
    INDEX
    Explanations

    use this file

    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
     spille
    -0.70
     supportive
    -0.69
    ustris
    -0.68
     Doch
    -0.68
     Think
    -0.68
    앙
    -0.68
     financial
    -0.67
    检查
    -0.66
     playing
    -0.66
    лектри
    -0.66
    POSITIVE LOGITS
     biennial
    0.88
     poland
    0.72
     bian
    0.72
     SLA
    0.70
     Ethio
    0.70
    bė
    0.69
     ALPH
    0.69
    Uruguay
    0.69
     архитек
    0.69
    歙
    0.68
    Activations Density 0.085%

    No Known Activations