© 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. 10921
    Prev
    Next
    INDEX
    Explanations

    multi-language common words and punctuation

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

    This neuron detects imperative action prompts—verbs or phrases that instruct the reader to do something (e.g. “click,” “download,” “contact us,” “enjoy,” etc.).

    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
    LY
    0.72
    }}},
    0.72
     Toch
    0.71
     usages
    0.70
    ωση
    0.68
    ેલી
    0.68
    oons
    0.67
    oja
    0.66
    uje
    0.66
    िनी
    0.65
    POSITIVE LOGITS
    т
    0.86
    kuat
    0.86
    および
    0.82
    Personensuche
    0.82
    ክ
    0.77
    दाता
    0.77
    こういう
    0.76
    または
    0.76
    وام
    0.75
    মেন্ট
    0.75
    Activations Density 0.001%

    No Known Activations