© 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-16K
    7. 13400
    Prev
    Next
    INDEX
    Explanations

    countries and Buddha

    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
    ﺩ
    1.42
    с
    1.38
    ្នុង
    1.35
    在上
    1.31
    de
    1.25
    кие
    1.25
     nextline
    1.24
     със
    1.22
    درا
    1.19
    栥
    1.19
    POSITIVE LOGITS
    ie
    1.35
    ️⃣
    1.33
     eerie
    1.20
    tig
    1.17
    oooooooo
    1.16
     abroad
    1.14
    tie
    1.11
    id
    1.09
    tı
    1.09
    و
    1.09
    Activations Density 0.063%

    No Known Activations