© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6112
    Prev
    Next
    INDEX
    Explanations

    run python scripts

    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
     squeezed
    0.69
     fud
    0.64
     કપ
    0.64
     Maid
    0.63
     Pads
    0.63
    ຍ
    0.61
    ppa
    0.61
     ELLE
    0.60
     cape
    0.60
     condiments
    0.60
    POSITIVE LOGITS
    اري
    0.78
     مستوى
    0.75
    osito
    0.74
     thi
    0.73
    umu
    0.72
    inesi
    0.72
    wany
    0.68
     심
    0.68
     свободно
    0.68
    ingo
    0.67
    Activations Density 0.012%

    No Known Activations