© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6010
    Prev
    Next
    INDEX
    Explanations

    tables summarizing languages

    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_31_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
    header
    0.61
    kol
    0.60
    ç
    0.57
    कोल
    0.54
    inio
    0.54
    min
    0.53
    lev
    0.53
    p
    0.53
    process
    0.53
    velden
    0.53
    POSITIVE LOGITS
    Arabic
    1.52
     English
    1.51
     Arabic
    1.45
     Spanish
    1.34
    English
    1.33
    Spanish
    1.33
     Hindi
    1.32
     영어
    1.30
     english
    1.27
     Urdu
    1.23
    Activations Density 0.064%

    No Known Activations