© 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. 84986
    Prev
    Next
    INDEX
    Explanations

    accessed through

    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
    怍
    -2.88
    蠖
    -2.67
     was
    -2.61
    ’).
    -2.52
    忖
    -2.50
    ಱ
    -2.44
    </strong>
    -2.42
    </h1>
    -2.41
     obiettivi
    -2.36
    淙
    -2.33
    POSITIVE LOGITS
    '
    2.91
    ↵
    2.73
    "
    2.70
    4
    2.69
    -
    2.31
     throng
    2.25
    過的
    2.23
    5
    2.23
     dostępne
    2.22
    すっ
    2.22
    Activations Density 0.007%

    No Known Activations