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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 445
    Prev
    Next
    INDEX
    Explanations

    punctuation and titles

    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_10/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
     unrelenting
    -1.99
     deliciosa
    -1.94
     EVERY
    -1.88
     perpetually
    -1.88
     oddly
    -1.87
     ALWAYS
    -1.86
     flawless
    -1.84
     markedly
    -1.84
     HUGE
    -1.83
     dazzling
    -1.82
    POSITIVE LOGITS
    despite
    2.19
    THERE
    2.16
    could
    2.05
     captivated
    2.05
     nuov
    1.98
     zoude
    1.96
    genodigd
    1.92
     a
    1.92
     cette
    1.86
    seems
    1.86
    Activations Density 0.003%

    No Known Activations