© 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. 41-GEMMASCOPE-2-RES-65K
    7. 13212
    Prev
    Next
    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     Kinn
    0.55
     Sill
    0.55
     vũ
    0.53
     ಮ
    0.50
     iha
    0.49
     sigma
    0.48
     resurrected
    0.48
     illetve
    0.48
    𝑉
    0.47
     wra
    0.46
    POSITIVE LOGITS
     تعمل
    0.61
     نک
    0.59
     befinden
    0.57
    Работа
    0.57
    readline
    0.56
    を起こ
    0.56
    під
    0.56
     เกิด
    0.55
    먹
    0.55
    姶
    0.55
    Activations Density 0.163%

    No Known Activations