Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8645
    Prev
    Next
    INDEX
    Explanations

    outboard motor parts

    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
     superstructure
    -0.82
     Fans
    -0.80
     interviewing
    -0.79
     diesel
    -0.77
    ätt
    -0.76
    STRUCTURE
    -0.73
    curities
    -0.73
    RequestMethod
    -0.72
     Func
    -0.72
    ните
    -0.70
    POSITIVE LOGITS
    Accel
    0.81
    OMC
    0.79
    znám
    0.76
    selectBy
    0.73
    hlás
    0.72
     jöv
    0.72
     hru
    0.71
     JOHNSON
    0.71
     Johnson
    0.69
    中です
    0.66
    Activations Density 0.012%

    No Known Activations