© 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. 479
    Prev
    Next
    INDEX
    Explanations

    ends with period

    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
    UCION
    -0.97
     where
    -0.90
    meisters
    -0.90
    在地上
    -0.89
     PyTuple
    -0.88
    ','',
    -0.86
     miel
    -0.85
    меты
    -0.85
    resultCode
    -0.85
    ที่
    -0.85
    POSITIVE LOGITS
    ។
    0.98
    とする
    0.95
    cdot
    0.94
     habido
    0.93
     gezeigt
    0.91
    をして
    0.88
     moſt
    0.88
    揾
    0.86
    鑷
    0.85
     angefangen
    0.85
    Activations Density 0.012%

    No Known Activations