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. 8038
    Prev
    Next
    INDEX
    Explanations

    `compiler` `attribute` `code`

    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
     during
    -1.02
     by
    -0.98
     through
    -0.90
     until
    -0.87
     although
    -0.84
     less
    -0.82
     from
    -0.81
     hoping
    -0.81
     on
    -0.79
     because
    -0.79
    POSITIVE LOGITS
    might
    0.99
    demokrat
    0.90
    Advantages
    0.85
     sánh
    0.84
     demokrat
    0.84
     REALLY
    0.84
     notamment
    0.84
    торт
    0.84
     WARNING
    0.83
     LOUIS
    0.83
    Activations Density 0.003%

    No Known Activations