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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68010
    Prev
    Next
    INDEX
    Explanations

    potential outcome verbs

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

    The neuron is selectively activating on modal auxiliary verbs (e.g. would, could, will) that express possibility or future action.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -1.41
     lunatic
    -1.31
     insulted
    -1.27
     these
    -1.25
     hierfür
    -1.22
    父の
    -1.17
    であり
    -1.16
     of
    -1.16
     are
    -1.16
     incluir
    -1.16
    POSITIVE LOGITS
    ทำให้
    1.88
     help
    1.88
     باعث
    1.79
     playera
    1.72
     allow
    1.71
     Sı
    1.60
    зраст
    1.55
     result
    1.55
     novin
    1.54
    讓
    1.52
    Activations Density 0.221%

    No Known Activations