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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109777
    Prev
    Next
    INDEX
    Explanations

    shapes and dimensions

    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
    findBy
    -0.78
    alike
    -0.76
     ۰
    -0.76
     passes
    -0.75
    ln
    -0.75
    away
    -0.73
    NonNull
    -0.73
    criminator
    -0.73
    auto
    -0.72
     noire
    -0.72
    POSITIVE LOGITS
     elliptic
    1.35
     elliptical
    0.98
     šir
    0.90
     broadly
    0.88
     broader
    0.85
     ovate
    0.82
     oblong
    0.81
     broadest
    0.80
     depressed
    0.79
     širo
    0.79
    Activations Density 0.016%

    No Known Activations