© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5107
    Prev
    Next
    INDEX
    Explanations

    foreign language text structures

    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_24_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
    姑
    0.70
    চিক
    0.70
    char
    0.68
     ways
    0.67
    Freq
    0.66
    select
    0.65
    erenza
    0.65
     water
    0.64
    湖
    0.64
    ص
    0.64
    POSITIVE LOGITS
     лиш
    0.82
     unmist
    0.82
     ਅ
    0.80
     обучения
    0.78
     музы
    0.77
     улы
    0.76
     определить
    0.76
     обуча
    0.76
     desactiv
    0.75
     любой
    0.75
    Activations Density 0.005%

    No Known Activations