© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9414
    Prev
    Next
    INDEX
    Explanations

    something unexpectedly

    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_262k_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
    š
    1.99
    ir
    1.85
    ö
    1.82
    до
    1.80
    ires
    1.79
    に
    1.77
    is
    1.75
    id
    1.69
    কে
    1.66
    as
    1.63
    POSITIVE LOGITS
     somew
    1.99
    ی
    1.75
    கூ
    1.70
    не
    1.61
    ки
    1.61
    悱
    1.59
    Sushi
    1.57
     enl
    1.55
     (#{
    1.54
     valide
    1.51
    Activations Density 0.003%

    No Known Activations