© 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. 21204
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

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

    The neuron fires strongly on open‐parenthesis tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     that
    -1.79
     may
    -1.45
    既に
    -1.38
    すでに
    -1.36
    loggen
    -1.34
     could
    -1.31
     also
    -1.30
    できれば
    -1.29
     ??????
    -1.27
     should
    -1.27
    POSITIVE LOGITS
    ="
    1.67
    OUTUBE
    1.67
    鰾
    1.59
     CGRectMake
    1.51
    傒
    1.49
    .,
    1.49
    byshev
    1.46
    ჻
    1.45
     auffi
    1.45
     Jehová
    1.44
    Activations Density 0.118%

    No Known Activations