© 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. 105567
    Prev
    Next
    INDEX
    Explanations

    go packages

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

    forward slashes in GitHub import paths or URL-like structures in Go 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
     a
    -2.03
    你这个
    -1.86
    _
    -1.82
    粜
    -1.81
     juſ
    -1.71
     to
    -1.63
     può
    -1.61
    んこ
    -1.60
     皇族
    -1.60
     unicórnio
    -1.59
    POSITIVE LOGITS
     it
    1.70
     is
    1.63
     time
    1.56
    </h4>
    1.55
     can
    1.54
    mathcal
    1.52
    t
    1.47
    ściu
    1.46
     quien
    1.45
    ）　
    1.39
    Activations Density 0.007%

    No Known Activations