© 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. 12558
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    不過
    2.59
    א
    2.28
    אנ
    2.17
    น
    2.11
    ن
    2.09
    ان
    2.06
    न
    2.05
    ע
    2.05
    ق
    2.00
    我
    1.95
    POSITIVE LOGITS
    ro
    2.22
    is
    2.11
    sh
    2.11
    ou
    2.00
    rifice
    1.99
    ii
    1.98
    it
    1.95
    ry
    1.94
    na
    1.94
    le
    1.92
    Activations Density 0.051%

    No Known Activations