© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 12706
    Prev
    Next
    INDEX
    Explanations

    why, explanation

    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
    Mol
    0.57
    Пол
    0.55
     mol
    0.54
     Пол
    0.54
    olja
    0.54
     ฮ
    0.53
     જુ
    0.53
    OL
    0.52
     pol
    0.52
    ulado
    0.52
    POSITIVE LOGITS
    㢼
    0.53
     منح
    0.51
    ˬ
    0.50
    uent
    0.49
     Kir
    0.49
    Kir
    0.49
    ellan
    0.48
    麒
    0.48
    AUC
    0.47
    дела
    0.46
    Activations Density 0.062%

    No Known Activations