© 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. 10-GEMMASCOPE-RES-131K
    7. 15142
    Prev
    Next
    INDEX
    Explanations

    is, followed by predicate

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

    The neuron consistently activates on the token “is” (as an identifier or part of predicate/function names) 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_10/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
    たちの
    -1.83
    to
    -1.79
     trabalhadores
    -1.76
     princípios
    -1.75
     móveis
    -1.75
     imó
    -1.74
     ativos
    -1.70
    鎌
    -1.66
     próprios
    -1.66
     Erkennt
    -1.66
    POSITIVE LOGITS
     ALWAYS
    2.13
     ONLY
    2.02
    ')}}">
    1.91
     anecd
    1.88
    AMIENTO
    1.81
     kwamba
    1.81
    antMatchers
    1.73
     /
    1.72
     Endlich
    1.70
     discul
    1.68
    Activations Density 0.007%

    No Known Activations