© 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. 14368
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    姨
    0.65
    bė
    0.54
    pony
    0.54
     sahaja
    0.53
     Marm
    0.51
     вой
    0.51
     pony
    0.51
     he
    0.50
     רבי
    0.50
     babe
    0.50
    POSITIVE LOGITS
     आइट
    0.65
    exposed
    0.57
    രിക്കുന്ന
    0.56
     வைத்த
    0.55
    㕲
    0.54
    ives
    0.52
    InBuffer
    0.52
    ючись
    0.52
     exposing
    0.52
    涝
    0.52
    Activations Density 0.000%

    No Known Activations