© 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. 26152
    Prev
    Next
    INDEX
    Explanations

    code variables and assignments

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

    The neuron activates on occurrences of variable names (identifiers) 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
     embrague
    -1.13
     zimní
    -1.09
     ním
    -1.06
    zbęd
    -0.98
     Wirken
    -0.93
    usado
    -0.92
     régal
    -0.92
     barev
    -0.91
    otros
    -0.91
     tramite
    -0.90
    POSITIVE LOGITS
     dier
    0.91
    eakers
    0.90
     talle
    0.89
    **/
    0.86
     stabile
    0.85
     sturdy
    0.85
    spira
    0.84
     weiß
    0.84
    landers
    0.83
    och
    0.82
    Activations Density 0.004%

    No Known Activations