© 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. 10-GEMMASCOPE-RES-131K
    7. 44182
    Prev
    Next
    INDEX
    Explanations

    technical file names and paths

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

    This neuron fires on programming identifiers and configuration keys—tokens that serve as names (e.g. variable, type, macro, or property names) rather than ordinary words.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     that
    -2.38
     puteți
    -1.55
    atação
    -1.55
    meteries
    -1.52
    ipzig
    -1.45
     rezultat
    -1.45
    vocable
    -1.44
     demografica
    -1.40
    น์
    -1.36
    nyttet
    -1.36
    POSITIVE LOGITS
    [
    1.58
    :
    1.39
    嘈
    1.34
    _
    1.30
    )
    1.27
    <sup>
    1.27
    dė
    1.24
     redenen
    1.23
    КУ
    1.23
    рони
    1.23
    Activations Density 0.374%

    No Known Activations