© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 142522
    Prev
    Next
    INDEX
    Explanations

    floppy ears or jowls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
    맇
    0.50
     จำ
    0.49
     முறையில்
    0.47
     သည်
    0.47
     יה
    0.47
    ম্‌
    0.46
     どう
    0.46
     wäre
    0.46
     নির্
    0.46
    蜒
    0.45
    POSITIVE LOGITS
    ва
    0.57
     Gard
    0.49
    ющие
    0.48
    ারক
    0.48
    5
    0.46
    2
    0.46
    裁
    0.46
    ержа
    0.45
    ادو
    0.45
    виде
    0.45
    Activations Density 0.000%

    No Known Activations