© 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. 16-GEMMASCOPE-2-RES-262K
    7. 145404
    Prev
    Next
    INDEX
    Explanations

    fundamental theorems and technical specs

    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
    Negative Logits
     floral
    0.57
     prism
    0.48
     devastating
    0.47
     radiography
    0.45
     pet
    0.45
    aklar
    0.45
    晖
    0.45
     Floral
    0.45
     film
    0.45
     flower
    0.45
    POSITIVE LOGITS
    ":{"
    0.60
    એસ
    0.56
    সম্যান
    0.55
    GBP
    0.54
    РУ
    0.54
    데이터
    0.54
    RIBUN
    0.54
    MQTT
    0.54
    ensureEqual
    0.53
    みんな
    0.52
    Activations Density 0.000%

    No Known Activations