© 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. 191380
    Prev
    Next
    INDEX
    Explanations

    Mendoza operations

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

    salt, fluid, outward, bend, systems, bubble

    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
     машине
    0.47
     Hamas
    0.47
    سبة
    0.45
    鲇
    0.44
    مرة
    0.43
    rás
    0.42
     сек
    0.42
     नेम
    0.41
    ítez
    0.41
    ikey
    0.41
    POSITIVE LOGITS
    異なります
    0.57
     tagReport
    0.50
    UTICAL
    0.49
    textColor
    0.48
     langt
    0.48
    फड
    0.48
    )){
    0.46
     wygląd
    0.46
    .);
    0.46
     Blut
    0.46
    Activations Density 0.000%

    No Known Activations