© 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. 25132
    Prev
    Next
    INDEX
    Explanations

    commands to get or do

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

    This neuron detects imperative “Get” or “get” commands introducing call-to-action phrases.

    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
     we
    -1.47
     from
    -1.18
     because
    -1.12
     after
    -1.09
     when
    -1.09
     actually
    -1.07
     since
    -1.05
     will
    -1.02
    makaian
    -1.00
     not
    -1.00
    POSITIVE LOGITS
    垰
    1.16
    のですか
    1.11
     berger
    1.11
     diriger
    1.02
     murale
    1.02
     palab
    1.01
     grotte
    1.00
    PMA
    1.00
     ✓
    0.99
    consulté
    0.98
    Activations Density 0.033%

    No Known Activations