© 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. 22-GEMMASCOPE-RES-131K
    7. 68292
    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_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
    lossians
    -2.77
    푙
    -2.72
    狳
    -2.53
    訁
    -2.52
    vantaged
    -2.45
    entiel
    -2.44
    杁
    -2.42
    🪤
    -2.42
    蹰
    -2.42
    恹
    -2.42
    POSITIVE LOGITS
    ↵
    3.61
    0
    3.16
    “
    2.81
    n
    2.61
    ;
    2.52
    \%
    2.48
    ‘
    2.45
    to
    2.44
    2
    2.41
    3
    2.41
    Activations Density 0.012%

    No Known Activations