© 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. 5105
    Prev
    Next
    INDEX
    Explanations

    whole word or line

    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
     kinn
    0.88
    ê
    0.84
    elfare
    0.83
    INSTDIR
    0.82
    ঙ্গা
    0.80
     iodide
    0.80
    ዌ
    0.79
    Ū
    0.79
    henol
    0.78
    潞
    0.77
    POSITIVE LOGITS
    za
    0.68
    介绍
    0.67
    pyplot
    0.67
    quadratic
    0.64
     Berk
    0.61
    ことから
    0.60
     waivers
    0.60
    ✍
    0.60
    ondas
    0.60
    দ
    0.59
    Activations Density 0.000%

    No Known Activations