© 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. 12-GEMMASCOPE-2-RES-262K
    7. 43674
    Prev
    Next
    INDEX
    Explanations

    instructions, types, input, case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_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
     wage
    0.85
    ’
    0.83
    '
    0.82
    enting
    0.80
    ysis
    0.78
    patial
    0.73
     Wage
    0.73
     Launcher
    0.72
     Newer
    0.71
     Fate
    0.70
    POSITIVE LOGITS
    ﺔ
    1.14
     불구하고
    1.01
    𝖺
    0.99
    有助于
    0.96
    avimo
    0.95
    ванне
    0.92
    телем
    0.90
    हदी
    0.89
    meth
    0.88
    ChessBot
    0.87
    Activations Density 0.000%

    No Known Activations