© 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. 15559
    Prev
    Next
    INDEX
    Explanations

    commands and prompts

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

    The neuron lights up on the principal content word (typically the main verb or key noun) of a clause or sentence.

    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
     Са
    0.80
    Р
    0.79
     Г
    0.76
     чого
    0.75
     COMMON
    0.74
     Cosa
    0.73
     Благодаря
    0.73
     Без
    0.72
     FARM
    0.71
    cook
    0.70
    POSITIVE LOGITS
     megawatts
    0.91
     vardı
    0.86
    側の
    0.83
    heath
    0.80
    がたくさん
    0.79
    ิ
    0.79
     dá
    0.79
     quarterbacks
    0.79
    纨
    0.79
    มากมาย
    0.78
    Activations Density 0.002%

    No Known Activations