© 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. 65363
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation

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

    The neuron fires on code identifiers (variable, function, or parameter names).

    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
    Nd
    -0.85
     data
    -0.80
    witzerland
    -0.79
    口水
    -0.78
    <em>
    -0.76
     Fällen
    -0.75
    тив
    -0.75
    crity
    -0.75
     with
    -0.74
    зывает
    -0.74
    POSITIVE LOGITS
     fossi
    0.90
     Moro
    0.90
     possi
    0.89
     člán
    0.88
    锲
    0.87
     Nook
    0.85
     syp
    0.85
     getNombre
    0.84
    ｒ
    0.84
     revan
    0.83
    Activations Density 0.023%

    No Known Activations