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. 8550
    Prev
    Next
    INDEX
    Explanations

    winning by a landslide

    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
     peł
    -0.95
     endlessly
    -0.84
     incorrectly
    -0.83
    cially
    -0.82
     actively
    -0.82
     etkili
    -0.81
    pagar
    -0.81
    ually
    -0.80
     pouvez
    -0.79
    optimal
    -0.78
    POSITIVE LOGITS
     by
    2.09
     convincingly
    1.67
     comfortably
    1.55
     handsomely
    1.52
     soundly
    1.41
     comfortable
    1.41
     convincing
    1.40
     easily
    1.37
     convin
    1.28
     easy
    1.27
    Activations Density 0.044%

    No Known Activations