© 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. 3356
    Prev
    Next
    INDEX
    Explanations

    Gibraltar

    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
     Formatting
    -0.70
    aragus
    -0.69
    絣
    -0.68
     fortfarande
    -0.66
     still
    -0.66
    روسية
    -0.64
     sabbat
    -0.64
    农村
    -0.64
     besitzen
    -0.63
    "></
    -0.63
    POSITIVE LOGITS
     Gibraltar
    2.16
    Gib
    1.40
    raltar
    1.30
     Gib
    1.21
     gib
    1.05
     جبل
    0.97
     Spanish
    0.93
    Spanish
    0.90
    gib
    0.88
     испан
    0.88
    Activations Density 0.007%

    No Known Activations