© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11354
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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_22/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
     serão
    -1.01
     Jind
    -0.98
    ⡱
    -0.98
    柔ら
    -0.95
     saludos
    -0.93
    ESTA
    -0.93
    椟
    -0.92
    䴀
    -0.92
     袋
    -0.91
    錾
    -0.91
    POSITIVE LOGITS
     not
    1.43
     even
    1.41
     at
    1.21
     on
    1.11
     or
    1.06
    からお
    1.00
     from
    0.99
     other
    0.98
     more
    0.97
     for
    0.95
    Activations Density 0.000%

    No Known Activations