© 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. 3262
    Prev
    Next
    INDEX
    Explanations

    contextual suffixes and foreign words

    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
    де
    1.55
    i
    1.52
    ли
    1.49
    ে
    1.49
    ุ
    1.44
    ${
    1.43
     bỏ
    1.43
    `
    1.39
    the
    1.37
    ung
    1.35
    POSITIVE LOGITS
    çı
    2.02
    ção
    1.95
    ן
    1.91
    cular
    1.88
    ਰ
    1.83
    ること
    1.80
    ğraf
    1.77
    ța
    1.77
    يل
    1.71
    geving
    1.71
    Activations Density 0.009%

    No Known Activations