© 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-IT
    5. 41-GEMMASCOPE-2-RES-16K
    7. 9403
    Prev
    Next
    INDEX
    Explanations

    eight

    np_max-act-logits · gemini-2.5-flash-lite

    eight

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ক্টো
    0.52
    <unused88>
    0.50
    jonen
    0.47
    DSS
    0.47
    ისუფ
    0.46
    ورٹی
    0.46
    junk
    0.46
    zeta
    0.45
    ಋ
    0.45
    <unused74>
    0.45
    POSITIVE LOGITS
     eight
    3.72
     Eight
    3.70
    八
    3.53
    Eight
    3.44
     八
    3.39
     вось
    3.39
     आठ
    3.14
     Eighth
    3.14
     eighth
    3.11
     oito
    3.11
    Activations Density 0.217%

    No Known Activations