© 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. 10558
    Prev
    Next
    INDEX
    Explanations

    code syntax and numbers

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

    The neuron fires on the word “Immediate,” i.e. a call-to-action urgency marker.

    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_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
     bilan
    0.64
    それを
    0.57
    findContacts
    0.56
     biblioteca
    0.55
    Packard
    0.52
    噓
    0.52
    segment
    0.52
    白い
    0.52
    フィルタ
    0.51
    arriv
    0.51
    POSITIVE LOGITS
     Malaysian
    0.59
    ليو
    0.56
     mythology
    0.56
     झाल्या
    0.54
    ሮ
    0.54
     नेशनल
    0.54
    ოლი
    0.54
     National
    0.54
     गेल्या
    0.53
     মুখোমুখি
    0.53
    Activations Density 0.000%

    No Known Activations