© 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. 13897
    Prev
    Next
    INDEX
    Explanations

    .

    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
     колек
    0.64
     تحديد
    0.59
    tség
    0.57
     Catawiki
    0.55
    鸵
    0.54
     colección
    0.54
     Botan
    0.53
     سائٹ
    0.52
    ributors
    0.52
    εσ
    0.52
    POSITIVE LOGITS
     появляется
    0.67
    environment
    0.57
    Saya
    0.57
    '$,
    0.56
     dessin
    0.54
    saya
    0.54
     drawing
    0.52
    acus
    0.50
    ScriptInterface
    0.50
     erscheint
    0.50
    Activations Density 0.000%

    No Known Activations