© 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. 10-GEMMASCOPE-RES-131K
    7. 6903
    Prev
    Next
    INDEX
    Explanations

    potential outcomes or conditions

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

    The neuron flags modal verbs and related words expressing possibility, permission, or potential (e.g., may, might, can, could, interfere, apply).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     zorro
    -1.49
     ankara
    -1.47
     volo
    -1.44
     diablo
    -1.43
     bilan
    -1.43
     loto
    -1.43
    brochen
    -1.39
     Buku
    -1.37
     carnet
    -1.33
     plac
    -1.31
    POSITIVE LOGITS
     which
    1.50
     is
    1.49
     was
    1.36
     information
    1.32
     junto
    1.30
     potential
    1.29
     be
    1.28
    Gilla
    1.26
     relaciona
    1.23
     potentially
    1.23
    Activations Density 0.070%

    No Known Activations