© 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. 118785
    Prev
    Next
    INDEX
    Explanations

    code comments and structure

    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
    ⠀⠀⠀⠀
    -0.76
     цело
    -0.75
    aży
    -0.74
    ganz
    -0.73
     بابا
    -0.72
     Coverage
    -0.71
     enumerated
    -0.71
     base
    -0.71
     деле
    -0.70
     супер
    -0.69
    POSITIVE LOGITS
     not
    0.83
    етки
    0.71
     at
    0.71
    agisse
    0.68
    دارة
    0.68
     continual
    0.66
     Similar
    0.66
     thirteen
    0.66
     главных
    0.66
     which
    0.65
    Activations Density 0.023%

    No Known Activations