© 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. 14320
    Prev
    Next
    INDEX
    Explanations

    model

    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
    ⁀
    0.59
     al
    0.57
     clar
    0.56
     алу
    0.56
     lâ
    0.55
    カスタム
    0.55
     itt
    0.54
     god
    0.54
    alda
    0.54
     repris
    0.54
    POSITIVE LOGITS
     Фу
    0.57
    恒
    0.53
    ifelse
    0.52
    ueur
    0.52
     تكبرها
    0.50
    feira
    0.50
    ambda
    0.49
     Зараз
    0.49
     Selasa
    0.49
    px
    0.48
    Activations Density 0.017%

    No Known Activations