© 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. 10573
    Prev
    Next
    INDEX
    Explanations

    assessing situations and outcomes

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

    The neuron detects semantically rich content words—especially descriptive nouns and adjectives that name qualities or specific concepts.

    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
    ل
    0.83
    ש
    0.77
    ларга
    0.71
    дың
    0.69
    ため
    0.69
    ている
    0.69
    א
    0.68
    ز
    0.68
    آ
    0.67
    д
    0.66
    POSITIVE LOGITS
     Ours
    0.80
    ing
    0.76
    as
    0.75
     Disaster
    0.75
     Og
    0.73
     Sherwood
    0.73
     homegrown
    0.73
     Elie
    0.73
     Politiker
    0.73
     Ehrlich
    0.73
    Activations Density 0.000%

    No Known Activations