© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127240
    Prev
    Next
    INDEX
    Explanations

    method selector

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

    The neuron fires on mentions of “method” (and related selector/objc_msgSend calls) in programming contexts, identifying when a question is discussing or naming a method or selector.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ®:
    -1.33
     banane
    -1.32
    uré
    -1.30
     raiſ
    -1.27
     cannes
    -1.25
     fusil
    -1.23
     lames
    -1.21
    遢
    -1.21
     vaqueros
    -1.19
     boute
    -1.18
    POSITIVE LOGITS
     to
    1.61
    onavir
    1.38
    }$
    1.34
    两者
    1.33
    idjan
    1.29
     }}$
    1.29
     aspetti
    1.23
    駛
    1.23
     importanti
    1.22
    émoc
    1.21
    Activations Density 0.030%

    No Known Activations