© 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. 129818
    Prev
    Next
    INDEX
    Explanations

    C++ code with special characters

    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
     every
    -1.79
     it
    -1.70
    蕷
    -1.59
    های
    -1.55
    ar
    -1.51
     cerca
    -1.45
     opravdu
    -1.45
    腻
    -1.43
     all
    -1.41
     Forder
    -1.40
    POSITIVE LOGITS
    となりました
    1.73
    侂
    1.65
    They
    1.59
    Compared
    1.51
    いぐるみ
    1.43
    AuthGuard
    1.43
     لأنه
    1.41
    阅读原文
    1.41
    publik
    1.41
    Maybe
    1.41
    Activations Density 0.016%

    No Known Activations