© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72872
    Prev
    Next
    INDEX
    Explanations

    ready or willing to proceed

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

    The neuron fires on words that express people’s eagerness or willingness (e.g. interested, ready, willing).

    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
    riad
    -0.98
    lou
    -0.89
     красиво
    -0.80
    pois
    -0.80
     étag
    -0.79
     écla
    -0.78
    Lou
    -0.77
     ſay
    -0.77
     Nacionales
    -0.76
    piles
    -0.75
    POSITIVE LOGITS
     receptive
    1.29
     recep
    1.26
     ready
    1.22
     sẵn
    1.16
     ANYTHING
    1.03
     پذ
    1.00
    READY
    0.98
     susceptibility
    0.97
    ceptibility
    0.95
     ANY
    0.94
    Activations Density 0.082%

    No Known Activations