© 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. 119015
    Prev
    Next
    INDEX
    Explanations

    tan, coat, color, pattern

    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
    ة
    2.31
    ing
    1.80
    ী
    1.54
    ש
    1.52
    ม
    1.45
    К
    1.45
    ı
    1.45
    ING
    1.42
    い
    1.27
    个
    1.27
    POSITIVE LOGITS
    ra
    1.29
    ot
    1.27
    ۳
    1.26
    at
    1.23
    are
    1.14
    ile
    1.13
     on
    1.09
    ’
    1.08
    res
    1.04
    arr
    1.03
    Activations Density 0.008%

    No Known Activations