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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14216
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    子公司
    0.50
    섭
    0.48
    収納
    0.47
     تاسو
    0.46
     terminal
    0.46
     termin
    0.45
    Terminal
    0.45
     مکمل
    0.45
     تاريخ
    0.44
     جنبي
    0.43
    POSITIVE LOGITS
     להת
    0.61
    বৎ
    0.59
    נק
    0.58
    ე
    0.58
    ്യം
    0.57
    ಾನೆ
    0.56
     ইত্যা
    0.56
    вих
    0.55
     SENT
    0.55
     încă
    0.55
    Activations Density 0.000%

    No Known Activations