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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11357
    Prev
    Next
    INDEX
    Explanations

    making, process, more

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

    The neuron fires on words that are action verbs (in various present‐tense or base forms) indicating some process or operation.

    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_24_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
    getColor
    0.73
     chant
    0.70
     comb
    0.69
     dado
    0.68
    блі
    0.68
     ત
    0.67
    cheat
    0.66
    lès
    0.66
    ces
    0.66
    hesion
    0.66
    POSITIVE LOGITS
     oversees
    0.93
    成為
    0.84
     affiliates
    0.82
     Overse
    0.80
     specifics
    0.80
    特朗普
    0.80
    摶
    0.79
     появилась
    0.79
     autochtones
    0.78
     콘텐츠
    0.77
    Activations Density 0.000%

    No Known Activations