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. 8115
    Prev
    Next
    INDEX
    Explanations

    control flow (if, elif, else, except)

    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
     because
    -1.17
     from
    -1.04
     hilang
    -0.98
     without
    -0.97
     Those
    -0.95
     so
    -0.93
     those
    -0.89
     Perhaps
    -0.89
     perhaps
    -0.86
    Those
    -0.85
    POSITIVE LOGITS
    elif
    2.05
     else
    1.91
    else
    1.91
     elif
    1.53
     же
    1.09
     epitome
    0.96
     rationale
    0.91
     quintessential
    0.90
        
    0.90
     perfecte
    0.89
    Activations Density 0.004%

    No Known Activations