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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20004
    Prev
    Next
    INDEX
    Explanations

    Denver

    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
    งิน
    -2.88
     “
    -2.59
    section
    -2.53
    
    -2.47
     Ее
    -2.42
    “
    -2.41
    はっきり
    -2.34
    猻
    -2.33
     Для
    -2.31
    錼
    -2.31
    POSITIVE LOGITS
    蟊
    2.52
    あります
    2.44
     is
    2.42
     какой
    2.28
    鸶
    2.23
    ztes
    2.22
    ᯾
    2.22
    岽
    2.14
    けると
    2.14
    轱
    2.11
    Activations Density 0.003%

    No Known Activations