© 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. 12-GEMMASCOPE-2-RES-16K
    7. 7605
    Prev
    Next
    INDEX
    Explanations

    anything particularly

    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
    ی
    1.76
    蚪
    1.49
    บุคคล
    1.32
     cuantos
    1.29
    SVC
    1.27
    猀
    1.23
    Ss
    1.22
    Fuj
    1.22
    댈
    1.21
     tequila
    1.20
    POSITIVE LOGITS
    al
    1.56
    il
    1.53
    on
    1.49
    ul
    1.47
    in
    1.44
     dė
    1.30
     doesn
    1.29
    ilise
    1.29
    ci
    1.27
     znacznie
    1.23
    Activations Density 0.322%

    No Known Activations