© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9014
    Prev
    Next
    INDEX
    Explanations

    examples of services

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

    The neuron fires on verbs that issue instructions or commands (imperatives).

    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
    Dude
    1.00
    ل
    0.96
    thati
    0.93
    ל
    0.92
    ليه
    0.86
     Dude
    0.84
    ტ
    0.81
    鲔
    0.81
    thol
    0.80
    نګه
    0.79
    POSITIVE LOGITS
     kerosene
    0.82
     hamster
    0.80
     laurel
    0.70
     medall
    0.70
     materialized
    0.69
     rám
    0.69
     desec
    0.69
     sly
    0.68
     hor
    0.68
     medal
    0.68
    Activations Density 0.000%

    No Known Activations