© 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. 33154
    Prev
    Next
    INDEX
    Explanations

    Programming code snippets

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

    The neuron is identifying programming identifiers—variable names, function names, and other code tokens.

    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
    iembre
    -0.96
     legt
    -0.86
     simplemente
    -0.86
    纫
    -0.85
     cayó
    -0.84
     prêtres
    -0.83
     食
    -0.80
    vericks
    -0.80
    zember
    -0.79
     pestaña
    -0.79
    POSITIVE LOGITS
     tersebut
    0.86
     Miki
    0.85
     politiker
    0.82
     thus
    0.80
     SUBSCRIBE
    0.79
    льники
    0.78
    ur
    0.77
     Boucher
    0.77
     now
    0.77
    urers
    0.76
    Activations Density 0.019%

    No Known Activations