© 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. 5969
    Prev
    Next
    INDEX
    Explanations

    Polish language content

    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
     anesthesia
    0.66
    आईसी
    0.63
     바라
    0.63
     playtime
    0.62
     完全
    0.62
    мония
    0.61
     가
    0.61
     cataract
    0.60
     Bereich
    0.59
     дори
    0.59
    POSITIVE LOGITS
    Im
    0.73
    Job
    0.72
    im
    0.71
     job
    0.69
    job
    0.69
     Job
    0.66
    ,:
    0.65
     wg
    0.65
    ini
    0.65
    ymi
    0.64
    Activations Density 0.052%

    No Known Activations