© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7904
    Prev
    Next
    INDEX
    Explanations

    code syntax and programming terms

    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
    ⭏
    -2.63
     to
    -2.47
    并在
    -2.42
    涐
    -2.28
    _{
    -2.20
    但是
    -2.19
    所说
    -2.17
    </h4>
    -2.14
    vereignty
    -2.14
    ल
    -2.13
    POSITIVE LOGITS
     adage
    2.64
    啣
    2.61
     multitudes
    2.55
    猻
    2.47
     Naturally
    2.44
    壜
    2.36
    時間
    2.33
     tentu
    2.30
     obstruct
    2.30
    」，
    2.28
    Activations Density 0.000%

    No Known Activations