© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 14755
    Prev
    Next
    INDEX
    Explanations

    old

    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
     গার্ম
    0.61
     nạn
    0.61
     विकलांग
    0.60
     পাকসেন
    0.59
    电子商务
    0.56
     chiropractor
    0.55
     protruding
    0.54
    闫
    0.54
    ㄝ
    0.54
     মাইক্র
    0.52
    POSITIVE LOGITS
     Poppy
    1.40
     Willow
    1.39
     Lily
    1.36
     Lola
    1.36
     Daisy
    1.34
    Lily
    1.29
    Willow
    1.26
     Olive
    1.24
     Stella
    1.24
     Iris
    1.24
    Activations Density 0.205%

    No Known Activations