© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 106115
    Prev
    Next
    INDEX
    Explanations

    jigsaw puzzle, coloring book, Walking Dead

    np_acts-logits-general · gemini-2.5-flash-lite

    jigsaw puzzle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^{
    0.52
     of
    0.46
     части
    0.46
    iever
    0.46
    ang
    0.45
    នៃ
    0.44
    ension
    0.44
    lee
    0.44
    á
    0.44
    lhe
    0.44
    POSITIVE LOGITS
    اگر
    0.48
    ན་
    0.47
    <0xAC>
    0.46
    মাল
    0.46
    ان
    0.44
    IOD
    0.44
     tüket
    0.44
    ন
    0.44
     pracov
    0.43
    אם
    0.42
    Activations Density 0.000%

    No Known Activations