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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41624
    Prev
    Next
    INDEX
    Explanations

    correlation between

    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
    蹰
    -3.09
    푙
    -2.91
     Gunakan
    -2.80
    狳
    -2.80
    entiel
    -2.72
    ᚻ
    -2.67
    鼙
    -2.67
    áculos
    -2.66
    iſe
    -2.64
    ariatric
    -2.61
    POSITIVE LOGITS
    ↵
    4.00
    “
    3.53
    ;
    3.00
    n
    2.97
    ‘
    2.91
    ↵↵↵
    2.86
    '
    2.84
    3
    2.78
    ).
    2.70
    ↵↵↵↵
    2.63
    Activations Density 0.008%

    No Known Activations