© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12597
    Prev
    Next
    INDEX
    Explanations

    commissioner of internal revenue

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

    The neuron chiefly activates on numeric tokens (e.g. years, dates, other digit sequences).

    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
     or
    -1.21
     in
    -1.11
    dziew
    -1.05
     if
    -1.00
    orElseThrow
    -0.97
    /
    -0.96
     at
    -0.94
     אותם
    -0.94
     reduces
    -0.93
    $
    -0.93
    POSITIVE LOGITS
     family
    1.53
     Beide
    1.22
     limpar
    1.13
     tensão
    1.06
     ansiedade
    1.05
     aço
    1.04
    }{%
    1.03
     velha
    1.02
    widetext
    1.02
    vacc
    1.02
    Activations Density 0.021%

    No Known Activations