© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 41490
    Prev
    Next
    INDEX
    Explanations

    variable declarations

    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
    ى
    1.45
    iti
    1.38
    ih
    1.31
    يت
    1.30
    的前提
    1.25
    ut
    1.23
    味道
    1.23
    '
    1.23
    ows
    1.23
    ında
    1.22
    POSITIVE LOGITS
    ্লাহ
    1.38
     Какой
    1.34
    堬
    1.27
    Вы
    1.25
    Какой
    1.23
     doméstica
    1.23
    屼
    1.22
    ﮑ
    1.20
     কিন্ত
    1.20
     ハン
    1.20
    Activations Density 0.002%

    No Known Activations