© 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-16K
    7. 7338
    Prev
    Next
    INDEX
    Explanations

    engine

    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_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
    ные
    2.03
    ный
    1.82
    ных
    1.77
    ного
    1.76
    ు
    1.68
    te
    1.67
    izontal
    1.67
    ник
    1.67
    erweise
    1.67
    此刻
    1.64
    POSITIVE LOGITS
    蚣
    1.96
    咛
    1.94
    嵋
    1.92
    songwriter
    1.83
    ない
    1.82
    ТЕ
    1.81
    ことになる
    1.80
    外的
    1.80
    𝔰
    1.79
     skladu
    1.77
    Activations Density 0.031%

    No Known Activations