© 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. 14757
    Prev
    Next
    INDEX
    Explanations

    Proper nouns

    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
     L
    0.80
     Sh
    0.79
    Sh
    0.77
     sh
    0.73
    sh
    0.68
    L
    0.68
    シャ
    0.67
    الن
    0.67
     ش
    0.66
     ল
    0.66
    POSITIVE LOGITS
    dor
    0.57
     DOR
    0.55
     বিবি
    0.54
     withdrawn
    0.54
    Ꮤ
    0.53
    withdraw
    0.53
    wC
    0.51
    ogran
    0.51
    wens
    0.50
    ogr
    0.50
    Activations Density 0.045%

    No Known Activations