© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84886
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    zeile
    -0.76
     thresh
    -0.70
     puppet
    -0.70
    Tors
    -0.69
     shellfish
    -0.69
     Saxony
    -0.69
    Evange
    -0.69
    dik
    -0.68
     Tors
    -0.68
    wirkungen
    -0.67
    POSITIVE LOGITS
     bool
    1.26
     bullet
    1.04
     cast
    1.02
     casting
    0.98
    bool
    0.97
     moulds
    0.97
     casts
    0.89
     bullets
    0.84
     mould
    0.82
     diameters
    0.82
    Activations Density 0.015%

    No Known Activations