© 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. 22-GEMMASCOPE-RES-131K
    7. 26495
    Prev
    Next
    INDEX
    Explanations

    Advanced Go, to determine, nucleophile

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

    code-related elements like function definitions, class declarations, and programming syntax.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects programming-language code tokens (e.g. function/class definitions and related identifiers).

    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
     kompati
    -1.20
     tambien
    -1.13
     warszawa
    -1.12
     rokok
    -1.09
     klien
    -1.04
     Юрий
    -1.02
     Projektu
    -1.02
    gerakan
    -1.00
    jalá
    -1.00
     também
    -1.00
    POSITIVE LOGITS
     on
    1.12
     with
    1.05
    Astronom
    1.02
     want
    1.02
    名の
    1.00
     up
    0.98
    aimerais
    0.98
    Ammonia
    0.97
    就職
    0.97
     change
    0.96
    Activations Density 0.004%

    No Known Activations