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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81
    Prev
    Next
    INDEX
    Explanations

    case when else

    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
    passes
    -0.85
    恍
    -0.83
    grave
    -0.82
     )(
    -0.82
    estimable
    -0.80
    ところに
    -0.79
    askin
    -0.79
    significant
    -0.77
    additional
    -0.76
    Duty
    -0.75
    POSITIVE LOGITS
     else
    1.43
    else
    1.15
     Else
    1.02
     in
    1.02
    Else
    0.92
    ELSE
    0.88
     otherwise
    0.84
     is
    0.84
    Portale
    0.81
     despite
    0.80
    Activations Density 0.003%

    No Known Activations