© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14345
    Prev
    Next
    INDEX
    Explanations

    connection url or share article

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

    The neuron is tuned to recognize technical programming/code tokens—especially JavaScript module imports, variable declarations, and function calls.

    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
     Nachfolger
    -1.16
     دیگران
    -1.16
     others
    -1.14
    äng
    -1.05
     delantero
    -1.05
     scrap
    -1.02
    êmes
    -1.02
     çev
    -1.01
     макия
    -1.01
     THESE
    -0.98
    POSITIVE LOGITS
    йтинг
    1.05
    ﻷ
    1.05
    mampuan
    1.04
    ség
    1.03
    rätt
    1.01
     rechter
    1.01
    Lato
    1.00
     גרם
    0.98
    ระบบ
    0.98
     mít
    0.98
    Activations Density 0.003%

    No Known Activations