© 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. 32827
    Prev
    Next
    INDEX
    Explanations

    instructions to view the

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

    This neuron spotlights call-to-action or instruction phrases (e.g. “please go to,” “view the LICENSE,” etc.).

    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
    蟥
    -1.24
     sué
    -1.09
    huur
    -1.02
    जय
    -1.00
     начин
    -0.99
     salão
    -0.98
     Livre
    -0.98
     Famille
    -0.98
     verão
    -0.97
     Japão
    -0.96
    POSITIVE LOGITS
    Instrucciones
    1.34
    Colore
    1.20
     our
    1.20
    Accademia
    1.17
     cipolla
    1.12
     μας
    1.04
     pendukung
    1.02
     pertumbuhan
    1.02
     vincere
    1.02
    tih
    0.99
    Activations Density 0.001%

    No Known Activations