© 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. 34-GEMMASCOPE-RES-131K
    7. 30828
    Prev
    Next
    INDEX
    Explanations

    perl pragmas, licenses, and code identifiers

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

    The neuron is keyed to spotting numeric literals (i.e. digit‐only tokens and version or other multi‐digit numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     歌
    -0.73
     الحره
    -0.70
    conceito
    -0.68
     الش
    -0.68
    conom
    -0.65
     Kue
    -0.64
    getBase
    -0.63
    UTER
    -0.63
     halide
    -0.63
     Publish
    -0.63
    POSITIVE LOGITS
    paralle
    0.68
     हाथ
    0.67
     Lohn
    0.67
    荟
    0.66
    akhstan
    0.66
    Colore
    0.66
    ดี
    0.66
    ষ্
    0.65
    spar
    0.64
    äischen
    0.63
    Activations Density 0.071%

    No Known Activations