© 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. 8329
    Prev
    Next
    INDEX
    Explanations

    unique characteristics, approaches, perspectives

    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
    ร
    1.89
    绻
    1.66
    مة
    1.61
    ల
    1.59
     וכ
    1.59
    티
    1.57
    ну
    1.56
    مان
    1.54
    ні
    1.53
    できます
    1.52
    POSITIVE LOGITS
    ás
    1.83
    ist
    1.75
    ait
    1.71
     sob
    1.71
    y
    1.67
     Tiến
    1.66
     Verbal
    1.66
    ști
    1.65
    KER
    1.63
    us
    1.63
    Activations Density 0.026%

    No Known Activations