© 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. 109925
    Prev
    Next
    INDEX
    Explanations

    error handling and conversion

    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
    uga
    -0.90
    (""
    -0.89
    OLDER
    -0.82
    uded
    -0.76
    ubo
    -0.74
    tión
    -0.73
    BIZ
    -0.73
    номи
    -0.71
    Verifier
    -0.71
     today
    -0.69
    POSITIVE LOGITS
    (""+
    0.86
     ruhig
    0.78
    ⎕
    0.75
     ()=>
    0.75
    HasBeen
    0.75
    িতে
    0.74
     náv
    0.74
    льни
    0.74
     ()=>{
    0.73
    وزيع
    0.73
    Activations Density 0.037%

    No Known Activations