© 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. 109801
    Prev
    Next
    INDEX
    Explanations

    code generation, versioning

    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
    inha
    -0.73
    tetten
    -0.72
    لب
    -0.71
    holder
    -0.69
    ưỡng
    -0.68
    ろう
    -0.66
    匿名使用者
    -0.66
    Про
    -0.66
    managers
    -0.65
    woli
    -0.65
    POSITIVE LOGITS
     absolue
    0.81
    啞
    0.71
     inputStream
    0.69
    学生的
    0.69
    documents
    0.67
     Highland
    0.66
    看书
    0.66
    QUOTE
    0.65
    dill
    0.65
    ichel
    0.65
    Activations Density 0.069%

    No Known Activations