© 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. 30601
    Prev
    Next
    INDEX
    Explanations

    code completion with punctuation

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

    This neuron activates on programming identifiers for types or classes (e.g. class names, protocol names, and other capitalized type 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_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
    ?!
    -1.70
    ?!"
    -1.48
    !?"
    -1.42
    ！？
    -1.40
    !?
    -1.37
    ?!”
    -1.28
     ?!
    -1.16
    ?!?!
    -1.15
    ？！
    -1.14
    !?!
    -1.04
    POSITIVE LOGITS
    ?,
    1.30
    (?)
    1.12
    ?.
    1.01
    ?;
    0.98
     ?,
    0.91
    ?/
    0.85
     (?)
    0.83
    ukų
    0.82
    ?-
    0.81
    -;
    0.81
    Activations Density 0.094%

    No Known Activations