© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12591
    Prev
    Next
    INDEX
    Explanations

    too well

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

    This neuron detects marketing call-to-action language—imperative or promotional verbs inviting the reader to do something (e.g. “search,” “apply,” “provide,” “explore,” 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
     кою
    0.71
     били
    0.69
    endants
    0.66
    큘
    0.66
     навер
    0.65
     Welding
    0.65
     chiar
    0.63
     გამოყენ
    0.63
    akel
    0.63
    प्रकारे
    0.63
    POSITIVE LOGITS
     Liebe
    0.82
     incentivize
    0.77
     Prensa
    0.76
    NASDAQ
    0.75
     relive
    0.75
     ease
    0.75
    駅
    0.73
     ambitious
    0.73
    件事
    0.73
    依旧
    0.73
    Activations Density 0.001%

    No Known Activations