© 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. 64767
    Prev
    Next
    INDEX
    Explanations

    code and headings

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

    This neuron detects programming-language keywords and tokens that introduce or invoke functions or methods (e.g. def, void, Write, on, etc.).

    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
     biela
    -1.88
     pantalon
    -1.72
     kalori
    -1.70
     torba
    -1.66
     españa
    -1.64
     romantis
    -1.63
     galeri
    -1.60
     mikrofon
    -1.58
     frança
    -1.57
     berken
    -1.56
    POSITIVE LOGITS
    u
    1.55
     R
    1.42
    le
    1.41
     L
    1.39
     S
    1.38
     While
    1.36
     De
    1.35
     J
    1.34
     C
    1.32
     D
    1.31
    Activations Density 0.001%

    No Known Activations