© 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. 15950
    Prev
    Next
    INDEX
    Explanations

    selected by

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

    The neuron is sensitive to words that function as modifiers or emphasis markers—comparatives, ordinals, intensifiers, and similar discourse‐heading tokens.

    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
    %。
    0.78
    नुसार
    0.75
    opss
    0.74
     selben
    0.74
    ং
    0.74
    ration
    0.73
    para
    0.72
    jur
    0.71
     cazul
    0.71
     turut
    0.71
    POSITIVE LOGITS
    
    0.81
     slumber
    0.76
    なんで
    0.75
     humanity
    0.74
     wry
    0.73
     tableware
    0.71
     brilliance
    0.71
     fickle
    0.71
    ἀ
    0.71
    ENSITY
    0.70
    Activations Density 0.000%

    No Known Activations