© 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. 40-GEMMASCOPE-2-RES-65K
    7. 1426
    Prev
    Next
    INDEX
    Explanations

    romanized chinese and characters

    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_40_width_65k_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
     diamètre
    0.45
     blanchâtre
    0.43
    𝓵
    0.43
     biofilms
    0.43
     follicles
    0.42
     rougeâtres
    0.42
     fistule
    0.41
     rougeâtre
    0.40
    ্যাস
    0.40
     outcrops
    0.40
    POSITIVE LOGITS
    day
    0.31
    ương
    0.29
     Pakistan
    0.29
    ‍
    0.29
     사회
    0.29
    ǔ
    0.28
    iy
    0.28
     United
    0.28
    政治
    0.28
    H
    0.28
    Activations Density 0.106%

    No Known Activations