© 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. 118813
    Prev
    Next
    INDEX
    Explanations

    Court served

    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
     kế
    -0.86
    سل
    -0.77
    サ
    -0.76
    Study
    -0.73
     Cristi
    -0.72
    Système
    -0.71
     Tsun
    -0.69
     ftate
    -0.69
    Lac
    -0.69
    Cuál
    -0.69
    POSITIVE LOGITS
    idy
    0.76
    zlich
    0.71
    burst
    0.71
    udnio
    0.70
    anding
    0.69
    cw
    0.69
    ッティング
    0.68
     wiel
    0.68
     donne
    0.67
    ancer
    0.67
    Activations Density 0.074%

    No Known Activations