© 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. 15809
    Prev
    Next
    INDEX
    Explanations

    code and technical text

    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
    োপাধ
    0.51
    бак
    0.51
    ⼈
    0.51
    Appendix
    0.51
    我们在
    0.50
    行業
    0.49
    理论
    0.49
    嬴
    0.49
    ciples
    0.48
    ም።
    0.48
    POSITIVE LOGITS
     caractér
    0.63
    aufen
    0.58
     Converter
    0.57
     プラ
    0.55
     présentant
    0.54
     flashed
    0.53
     الدولية
    0.53
     internationaux
    0.53
    NEE
    0.52
     prototype
    0.52
    Activations Density 0.000%

    No Known Activations