© 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. 119171
    Prev
    Next
    INDEX
    Explanations

    engines and engine types

    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
     Kosten
    -0.77
     malignancy
    -0.75
     conhe
    -0.75
    🦠
    -0.73
     Administração
    -0.70
     Gnade
    -0.70
     dislocation
    -0.69
    hesda
    -0.69
     humility
    -0.69
    Pa
    -0.69
    POSITIVE LOGITS
     Briggs
    1.21
     Kohler
    1.05
     brig
    0.90
    governor
    0.88
     Vanguard
    0.85
    Brig
    0.85
    Lister
    0.84
     pulsa
    0.83
     governed
    0.81
     recoil
    0.79
    Activations Density 0.013%

    No Known Activations