© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 192283
    Prev
    Next
    INDEX
    Explanations

    actual information content

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    と考え
    0.39
    귤
    0.39
     memastikan
    0.39
     ต้อง
    0.38
     perse
    0.38
    ambarkan
    0.38
     নিয়ন্ত্রণে
    0.38
    "。
    0.37
    状態
    0.37
    堬
    0.37
    POSITIVE LOGITS
    centering
    0.46
     ပ
    0.45
    ’
    0.44
    Copies
    0.43
    alum
    0.43
    isted
    0.42
    tree
    0.41
    criptors
    0.41
    Website
    0.41
    Globe
    0.40
    Activations Density 0.000%

    No Known Activations