© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2206
    Prev
    Next
    INDEX
    Explanations

    ranging from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
     лу
    0.61
    版本
    0.58
     камень
    0.57
    Equivalent
    0.56
    Copper
    0.56
     Capitals
    0.54
    绔
    0.54
    ur
    0.54
     exud
    0.54
    並
    0.53
    POSITIVE LOGITS
    Seat
    0.61
    oming
    0.61
    立つ
    0.60
    itza
    0.59
     Sitting
    0.57
    Sitting
    0.57
     satta
    0.57
     Houses
    0.57
    ěst
    0.57
     Dais
    0.57
    Activations Density 0.279%

    No Known Activations