© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15642
    Prev
    Next
    INDEX
    Explanations

    Crisis Text Line

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

    The neuron detects occurrences of the word “crisis” (including in multi-word headings like “crisis intervention”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the word "crisis" in various contexts, particularly in formal or institutional settings.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of crises, especially in contexts of counseling, intervention, or support services.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    mons
    0.66
    ╮
    0.61
    のを
    0.58
    iazioni
    0.57
    ══
    0.57
     Sandals
    0.57
     Constructions
    0.57
     কেউ
    0.56
     Passion
    0.54
    monton
    0.54
    POSITIVE LOGITS
     cris
    0.64
     khác
    0.61
     crisp
    0.59
    危机
    0.55
     flames
    0.55
    ב
    0.55
    stav
    0.55
    Integrante
    0.55
     bomb
    0.54
     нрав
    0.54
    Activations Density 0.021%

    No Known Activations