© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9632
    Prev
    Next
    INDEX
    Explanations

    Valorant gameplay

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

    The neuron activates mainly on named-entity tokens such as organization names, program titles, brand sponsors, and proper names.

    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
    tiden
    0.70
    𝘵
    0.62
    dı
    0.61
    дри
    0.60
    تين
    0.59
    ļu
    0.59
    تها
    0.57
     अध्या
    0.57
    enay
    0.57
    emás
    0.57
    POSITIVE LOGITS
    ians
    0.90
    رر
    0.79
    r
    0.77
    hythm
    0.75
    izontal
    0.75
     sauvegard
    0.70
    therly
    0.68
    itical
    0.68
    rrrr
    0.68
    thern
    0.66
    Activations Density 0.628%

    No Known Activations