© 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. 22-GEMMASCOPE-RES-131K
    7. 12173
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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_22/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
    无聊
    -0.85
    yak
    -0.83
    nemy
    -0.82
     Semoga
    -0.81
     HOLL
    -0.79
    므
    -0.79
    カッコいい
    -0.78
    erex
    -0.78
    ricks
    -0.77
    tsu
    -0.76
    POSITIVE LOGITS
    hawatir
    1.09
     européennes
    0.95
    ˗
    0.93
     родился
    0.91
     from
    0.90
     categorized
    0.85
     laaj
    0.84
    jaci
    0.84
     vägen
    0.84
    🥉
    0.84
    Activations Density 0.017%

    No Known Activations