© 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. 34-GEMMASCOPE-RES-131K
    7. 109918
    Prev
    Next
    INDEX
    Explanations

    configuration options

    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
     dikirim
    -0.79
    ackerel
    -0.74
     menceritakan
    -0.73
     IEnumerator
    -0.71
     září
    -0.71
    ཞ
    -0.70
     Arzneimit
    -0.69
    unov
    -0.69
    实的
    -0.69
     Clemens
    -0.69
    POSITIVE LOGITS
    CONFIG
    1.13
     CONFIG
    1.12
     configs
    0.86
     config
    0.83
     EXPORT
    0.82
     Symbol
    0.77
     configura
    0.77
    config
    0.76
    Config
    0.75
    选项
    0.75
    Activations Density 0.109%

    No Known Activations