© 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. 118618
    Prev
    Next
    INDEX
    Explanations

    dropped out of school

    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
    ensio
    -0.71
     mencu
    -0.69
    英語版
    -0.66
     performance
    -0.66
    生的
    -0.65
    奏
    -0.65
     coming
    -0.64
     people
    -0.63
     sport
    -0.63
     managed
    -0.63
    POSITIVE LOGITS
     out
    0.86
     obsequ
    0.80
     CVE
    0.77
    corpor
    0.73
    outSlope
    0.72
    
    0.71
    :--
    0.70
     YAP
    0.70
     itinéraires
    0.69
    setStyle
    0.68
    Activations Density 0.054%

    No Known Activations