© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8867
    Prev
    Next
    INDEX
    Explanations

    creating

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

    This neuron responds to words that denote actions, duties, or tasks (e.g. “working,” “responsibilities,” “check,” “redeem,” “used”).

    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
    lig
    0.76
    liy
    0.71
    לי
    0.69
     ВО
    0.66
    lier
    0.64
    גר
    0.64
     र
    0.63
     優
    0.63
     Тя
    0.63
     intercal
    0.62
    POSITIVE LOGITS
     nervioso
    0.95
     ciudadanos
    0.89
    ar
    0.84
     screws
    0.80
     vestir
    0.80
     Nobody
    0.79
    am
    0.78
    Nobody
    0.77
     agir
    0.75
     niemand
    0.75
    Activations Density 0.000%

    No Known Activations