© 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. 65502
    Prev
    Next
    INDEX
    Explanations

    code syntax and programming constructs

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

    The neuron fires on single‐character identifiers or variable names (e.g. “b”, “d”, “h”, “Base” when it’s used as a one‐segment name) 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_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
     all
    -1.19
    lerde
    -0.94
     similar
    -0.89
    lehre
    -0.88
    戦士
    -0.85
     as
    -0.84
     italien
    -0.82
    tokio
    -0.81
    createUser
    -0.81
     potentially
    -0.81
    POSITIVE LOGITS
    !—
    0.98
    嗑
    0.91
    ilarang
    0.90
     に関する
    0.88
    するので
    0.88
    􀀀
    0.87
     felpa
    0.86
     multiuso
    0.86
     مستق
    0.85
     beteiligt
    0.85
    Activations Density 0.148%

    No Known Activations