© 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. 34-GEMMASCOPE-RES-131K
    7. 107208
    Prev
    Next
    INDEX
    Explanations

    function calls after return

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

    The neuron fires on code‐style punctuation and delimiter tokens (e.g. parentheses, equals signs, colons, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     first
    -1.07
     started
    -0.94
     just
    -0.94
    답
    -0.92
     high
    -0.91
     both
    -0.91
     emphasized
    -0.88
     texinfo
    -0.86
     so
    -0.84
    gangenen
    -0.84
    POSITIVE LOGITS
    elif
    1.06
    ARMA
    1.05
    très
    1.03
    generally
    1.03
     atrak
    1.02
    gebühr
    0.96
     STORM
    0.96
     trám
    0.95
    DOF
    0.95
    epy
    0.95
    Activations Density 0.008%

    No Known Activations