© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16440
    Prev
    Next
    INDEX
    Explanations

    define variable or property assignment

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

    The neuron flags tokens involved in setting or defining values in code (e.g. assignments and constant/macros definitions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     tromper
    -1.18
    蟥
    -1.16
     nettoyer
    -1.16
    ğun
    -1.14
     imprimer
    -1.13
     avoient
    -1.12
     recensement
    -1.11
     refroid
    -1.10
     mélanger
    -1.09
     réinitial
    -1.09
    POSITIVE LOGITS
     also
    1.26
     one
    1.22
     even
    1.19
     =
    1.15
     is
    1.12
     didn
    1.08
     definitely
    1.04
    ka
    1.03
     certainly
    1.02
    is
    1.02
    Activations Density 0.002%

    No Known Activations