© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75953
    Prev
    Next
    INDEX
    Explanations

    unified combination

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

    Valorant, focal hepatic, mimicking well

    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
    Negative Logits
    beda
    0.48
    箸
    0.46
     ל
    0.44
    佢
    0.44
    商品
    0.43
    ガチャ
    0.43
     फ्रॉम
    0.43
    这场
    0.42
    刨
    0.42
     машину
    0.42
    POSITIVE LOGITS
     basadas
    0.51
     isTestSource
    0.50
     veineux
    0.45
     ”,
    0.44
    ],”
    0.43
     รวมถึง
    0.43
     ڈاک
    0.42
    িনবার্গ
    0.42
     ذاتی
    0.41
     基于
    0.41
    Activations Density 0.002%

    No Known Activations