© 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. 3309
    Prev
    Next
    INDEX
    Explanations

    United States

    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
    Conclusión
    -0.87
    Atentamente
    -0.84
    Causas
    -0.80
     chose
    -0.79
    Invoker
    -0.79
     tedious
    -0.77
     copious
    -0.77
     vowed
    -0.75
    ÍNDICE
    -0.74
    Mujer
    -0.73
    POSITIVE LOGITS
     Reis
    0.90
    획
    0.89
    ormal
    0.82
     новых
    0.78
     Â
    0.76
    tual
    0.76
    median
    0.76
     carretera
    0.76
     $
    0.76
     вас
    0.76
    Activations Density 0.061%

    No Known Activations