© 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. 13973
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     Màu
    0.49
    ocurrencies
    0.46
     inodes
    0.45
    丼
    0.41
    ０
    0.41
    asionally
    0.41
    符
    0.41
     チャ
    0.40
     BatchNorm
    0.40
    အား
    0.40
    POSITIVE LOGITS
     eleven
    0.47
     eight
    0.46
     five
    0.46
     ten
    0.46
     seven
    0.44
     thousands
    0.44
     hundreds
    0.44
     three
    0.43
     six
    0.42
     scared
    0.42
    Activations Density 0.068%

    No Known Activations