© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109892
    Prev
    Next
    INDEX
    Explanations

    shaved ice dessert

    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
     milking
    -0.84
    姆
    -0.73
     Warbler
    -0.73
     lobsters
    -0.72
    witches
    -0.71
     Brems
    -0.71
    rfloor
    -0.70
    boro
    -0.70
     thigh
    -0.69
     Merced
    -0.69
    POSITIVE LOGITS
    🍧
    0.96
    Ice
    0.93
     Ice
    0.92
     shaved
    0.85
     tamar
    0.85
     ice
    0.80
     Kool
    0.76
     sno
    0.75
    sev
    0.74
    sno
    0.74
    Activations Density 0.019%

    No Known Activations