© 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. 102985
    Prev
    Next
    INDEX
    Explanations

    code structure and specific names

    np_acts-logits-general · gemini-2.5-flash-lite

    method calls related to data binding or API initialization in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    蟥
    -2.61
    iczna
    -2.48
     Partly
    -2.47
    1
    -2.45
     Intended
    -2.31
     Только
    -2.30
     Impressive
    -2.28
     Descri
    -2.27
    立刻
    -2.25
    但她
    -2.22
    POSITIVE LOGITS
    ’，
    2.84
    ᠁
    2.50
    谈判
    2.50
    s
    2.48
    身边的
    2.41
    튿
    2.41
     efic
    2.36
    ים
    2.23
    这样一个
    2.19
    他们在
    2.17
    Activations Density 0.000%

    No Known Activations