© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3832
    Prev
    Next
    INDEX
    Explanations

    XML `x:Class` attributes

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

    This neuron responds to mentions of digital book formats and publication metadata (e.g. PDF, ePub, Online, Kindle, Bücher, tome).

    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_24_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
    华人
    0.65
    휀
    0.64
    courts
    0.61
    大街
    0.58
     हेल्प
    0.58
    ổng
    0.57
     geometrically
    0.57
    中华
    0.56
    팁
    0.55
    profits
    0.55
    POSITIVE LOGITS
     Kindle
    0.79
     scritt
    0.78
     invita
    0.75
     kindle
    0.75
     只
    0.72
     ISBN
    0.72
     bestseller
    0.71
     isbn
    0.71
     היה
    0.71
     കഥ
    0.70
    Activations Density 0.000%

    No Known Activations