© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5636
    Prev
    Next
    INDEX
    Explanations

    output followed by punctuation or file names

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

    This neuron detects the idiomatic expression “out in full force.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viagem
    0.63
    gek
    0.60
    レ
    0.60
     maak
    0.59
    荃
    0.59
    anna
    0.59
    劃
    0.57
    juč
    0.57
    ાવી
    0.57
    スク
    0.56
    POSITIVE LOGITS
     OUT
    0.84
     निकलते
    0.80
     निकलता
    0.79
     loud
    0.73
    rages
    0.72
    OUT
    0.71
     out
    0.71
    sibling
    0.68
     of
    0.68
    т
    0.68
    Activations Density 0.282%

    No Known Activations