© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39225
    Prev
    Next
    INDEX
    Explanations

    code structure and data manipulation

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

    This neuron detects leading indentation whitespace (sequences of spaces used to indent code blocks).

    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
     phénom
    -1.62
     Ministre
    -1.40
     parfü
    -1.38
     geschenk
    -1.35
     reizen
    -1.34
     mengumumkan
    -1.34
     transparentes
    -1.33
    є
    -1.33
     obrázok
    -1.33
     allerlei
    -1.32
    POSITIVE LOGITS
     it
    1.98
     current
    1.79
     results
    1.75
     new
    1.73
     result
    1.70
     resulting
    1.65
     wanted
    1.64
     want
    1.63
     entire
    1.61
     needed
    1.58
    Activations Density 0.037%

    No Known Activations