© 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. 10-GEMMASCOPE-RES-131K
    7. 612
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and scientific terms

    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
    摭
    -3.41
    苼
    -3.23
    亖
    -2.84
    来自于
    -2.84
    阄
    -2.78
    OUTUBE
    -2.77
    産の
    -2.73
    嵓
    -2.72
    辄
    -2.70
    ⏑
    -2.70
    POSITIVE LOGITS
    1
    3.94
     This
    3.92
    \
    3.47
    4
    3.19
    ти
    3.06
    6
    2.84
    At
    2.80
    It
    2.75
    ."
    2.73
    Blaðsíða
    2.69
    Activations Density 0.018%

    No Known Activations