© 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. 107615
    Prev
    Next
    INDEX
    Explanations

    coach told

    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
     bowl
    -1.12
    bowl
    -0.79
     Bowl
    -0.79
    Bowl
    -0.77
     Purchases
    -0.74
     bowls
    -0.74
    ITT
    -0.72
     bowlers
    -0.72
     basin
    -0.70
    veren
    -0.67
    POSITIVE LOGITS
     Rivals
    1.77
     Scout
    1.36
    Ri
    1.28
    Scout
    1.16
     recruiting
    1.02
     scholarship
    0.97
     scout
    0.96
     Scholarship
    0.95
     Composite
    0.93
     composite
    0.91
    Activations Density 0.037%

    No Known Activations