© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84433
    Prev
    Next
    INDEX
    Explanations

    void onCreate method

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

    The neuron fires on the “void” keyword in method signatures—that is, it detects declarations of methods returning void.

    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
    嚒
    -1.84
     grupp
    -1.72
    Ensuite
    -1.70
     spesifik
    -1.66
     seront
    -1.65
    1
    -1.65
     nivå
    -1.63
     rembourse
    -1.60
     dando
    -1.59
     ansik
    -1.59
    POSITIVE LOGITS
     to
    2.25
     of
    2.17
     before
    2.06
     on
    2.05
     when
    1.95
     during
    1.88
     from
    1.87
     There
    1.73
     as
    1.73
     for
    1.70
    Activations Density 0.002%

    No Known Activations