© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12436
    Prev
    Next
    INDEX
    Explanations

    device model information

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

    The neuron activates on “Sent from…” style footer signatures (e.g. “Sent from my iPhone,” “Sent from Jack Bauer’s PDA”).

    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
     квіт
    0.58
    鍰
    0.57
    Дата
    0.55
    नेशनल
    0.55
    csvStream
    0.54
     таксама
    0.53
    たとえば
    0.53
    даг
    0.51
    níku
    0.51
    ottes
    0.50
    POSITIVE LOGITS
     moved
    0.66
    elde
    0.59
     Woodland
    0.58
     ဆ
    0.57
     الصور
    0.57
    Moved
    0.57
     Jericho
    0.57
     Moved
    0.57
     نتیجہ
    0.56
    ez
    0.54
    Activations Density 0.001%

    No Known Activations