© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64490
    Prev
    Next
    INDEX
    Explanations

    parameter, argument, operand

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

    This neuron fires on occurrences of “Parameter” or “Argument” in error or exception messages.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    grains
    -1.25
    盌
    -1.13
    ändigen
    -1.12
    quakes
    -1.10
    hā
    -1.09
    château
    -1.08
     ikan
    -1.08
    知道
    -1.07
    hardy
    -1.07
     már
    -1.05
    POSITIVE LOGITS
     poorly
    1.23
    In
    1.23
     "",
    1.21
    不僅
    1.19
     ['./
    1.18
    Hilsen
    1.13
    antar
    1.11
    o
    1.10
    兩個
    1.05
    质疑
    1.05
    Activations Density 0.001%

    No Known Activations