© 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. 118891
    Prev
    Next
    INDEX
    Explanations

    dashboard and interior components

    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
     trailers
    -0.88
    Embeddable
    -0.84
     tires
    -0.82
    aksanaan
    -0.81
     trailer
    -0.80
    🍤
    -0.79
    bę
    -0.77
    ejb
    -0.76
    מוד
    -0.75
    ((&
    -0.75
    POSITIVE LOGITS
     dashboard
    1.70
     dash
    1.52
     Dashboard
    1.41
    dash
    1.33
    dashboard
    1.32
    Dashboard
    1.29
     Piano
    1.15
     dashboards
    1.09
    Dash
    1.09
     Dash
    1.07
    Activations Density 0.010%

    No Known Activations