© 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. 35236
    Prev
    Next
    INDEX
    Explanations

    code, functions, and technical queries

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

    This neuron fires on programming‐language tokens—especially JavaScript code keywords, function definitions, braces, and other code syntax.

    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
     salarios
    -1.06
     sucesso
    -1.03
    ῖν
    -1.02
    Oid
    -1.02
     bizarre
    -1.01
     салона
    -1.00
     сотрудников
    -1.00
     creat
    -1.00
    ψε
    -0.99
    ఉ
    -0.98
    POSITIVE LOGITS
     their
    1.48
     or
    1.47
     While
    1.22
     adds
    1.17
     if
    1.16
     for
    1.16
    While
    1.13
     helps
    1.10
     helping
    1.10
     makes
    1.09
    Activations Density 0.008%

    No Known Activations