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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7883
    Prev
    Next
    INDEX
    Explanations

    spin chains and quantum phenomena

    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
     GridView
    -0.88
    HEC
    -0.77
    lcm
    -0.74
    livion
    -0.73
    proc
    -0.72
    bloom
    -0.71
    tvb
    -0.71
    Holiday
    -0.71
    Angular
    -0.70
    UIN
    -0.70
    POSITIVE LOGITS
     sites
    1.02
     chain
    0.98
     Chains
    0.94
     szcze
    0.93
     site
    0.88
     chains
    0.87
     Egger
    0.82
     respiración
    0.81
     Lut
    0.79
    chain
    0.78
    Activations Density 0.067%

    No Known Activations