© 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. 12371
    Prev
    Next
    INDEX
    Explanations

    programming 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
    <>
    -1.06
    8
    -0.93
     dreht
    -0.93
    9
    -0.85
     among
    -0.85
    (/^
    -0.85
    3
    -0.85
     (!__
    -0.85
    7
    -0.83
     other
    -0.83
    POSITIVE LOGITS
     Qualquer
    1.13
    tôi
    1.05
    Immediately
    1.03
    ｫ
    0.95
     ἐκ
    0.93
    hình
    0.91
    Không
    0.91
    Curiosidades
    0.91
    Czy
    0.90
    БА
    0.90
    Activations Density 0.011%

    No Known Activations