© 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. 129293
    Prev
    Next
    INDEX
    Explanations

    code components such as classes and attributes

    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
     rých
    -2.45
    攻擊
    -2.34
     splits
    -2.34
    aphne
    -2.31
     pleas
    -2.27
    ку
    -2.25
     megfe
    -2.23
     dôle
    -2.22
    时间
    -2.20
    一百
    -2.19
    POSITIVE LOGITS
    芣
    2.56
    欵
    2.55
     inade
    2.55
     they
    2.47
     vives
    2.47
     violen
    2.39
     decis
    2.38
    d
    2.36
    玗
    2.36
    </h3>
    2.33
    Activations Density 0.002%

    No Known Activations