© 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. 9766
    Prev
    Next
    INDEX
    Explanations

    value

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

    The neuron flags words naming or inviting interaction with media content or resource actions (e.g. Photo, Video, Download, Send inquiry).

    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
     কাপড়
    0.58
     Phú
    0.55
     Nitro
    0.54
    Alph
    0.54
     गाड़ी
    0.54
     Ivory
    0.54
    ;++
    0.53
     Nob
    0.53
     Rutherford
    0.53
    Herbert
    0.53
    POSITIVE LOGITS
     fü
    0.58
     obtenue
    0.57
    webp
    0.57
    咳
    0.55
     kre
    0.54
     başlay
    0.54
    obtain
    0.54
    ЛА
    0.53
    ഭവ
    0.53
     abge
    0.52
    Activations Density 0.000%

    No Known Activations