© 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. 13986
    Prev
    Next
    INDEX
    Explanations

    Gemma

    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
     monitored
    0.74
    蜡
    0.66
     polymorphic
    0.63
     чаще
    0.60
     popsicle
    0.60
     sapphire
    0.60
    рованы
    0.60
     computed
    0.59
    жная
    0.59
    监测
    0.59
    POSITIVE LOGITS
     lò
    0.95
     pò
    0.89
     sì
    0.89
    ò
    0.89
     cioè
    0.88
    èl
    0.86
    ì
    0.85
     ł
    0.82
     Vì
    0.81
    òi
    0.81
    Activations Density 0.005%

    No Known Activations