© 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. 8308
    Prev
    Next
    INDEX
    Explanations

    Crisis Lifeline

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

    The neuron is especially sensitive to promotional language—positive‐evaluation and call‐to‐action words used in ad‐style or marketing copy.

    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
     &
    0.73
    ↵
    0.60
    </b>
    0.54
    elf
    0.52
    则是
    0.52
     Parm
    0.52
    ↵↵↵
    0.51
    ,
    0.51
    өр
    0.50
    개의
    0.50
    POSITIVE LOGITS
    িকাংশ
    0.70
     sowie
    0.70
     اهلا
    0.70
     altra
    0.70
     እንዲሁም
    0.70
     শ্ব
    0.67
     apice
    0.67
     oraz
    0.64
     serta
    0.64
     Anmeldung
    0.64
    Activations Density 0.052%

    No Known Activations