© 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. 99733
    Prev
    Next
    INDEX
    Explanations

    fif, thir, numbers, ordinals

    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
    ↵↵
    -2.75
    ଃ
    -2.61
    ↵
    -2.48
    瑧
    -2.45
     multitude
    -2.28
     hebben
    -2.25
     pracow
    -2.25
     クラブ
    -2.25
    งิน
    -2.20
    转身
    -2.17
    POSITIVE LOGITS
    ’
    2.73
    We
    2.53
    <bos>
    2.52
    
    2.31
    </h3>
    2.31
    that
    2.23
    䛗
    2.19
    Of
    2.17
    就像
    2.17
    section
    2.16
    Activations Density 0.008%

    No Known Activations