© 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. 16370
    Prev
    Next
    INDEX
    Explanations

    aggregate load, function parameters, search environments, need them

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

    This neuron fires strongly on individual keywords that appear in commercial or promotional contexts (e.g. product, service, or offer terms).

    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
    ERING
    0.80
    ())));
    0.76
     முழு
    0.75
    BAS
    0.75
     estatal
    0.75
     duelo
    0.75
    IGNORE
    0.74
    Generic
    0.73
     sacerdote
    0.73
     storico
    0.72
    POSITIVE LOGITS
    fall
    0.78
    ট
    0.78
    до
    0.74
    ulat
    0.71
    and
    0.70
    ained
    0.70
    ancy
    0.69
    ತಾ
    0.69
     therefrom
    0.68
    •
    0.68
    Activations Density 0.001%

    No Known Activations