© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6869
    Prev
    Next
    INDEX
    Explanations

    embedding html or content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    骉
    -3.28
     he
    -3.05
    姈
    -2.92
    ྄
    -2.67
    蓠
    -2.53
    了一口
    -2.50
    起床
    -2.47
    🫃
    -2.47
     мужская
    -2.45
     especialidad
    -2.44
    POSITIVE LOGITS
    ⦊
    3.13
     ambayo
    2.83
    𖥦
    2.77
    ڧ
    2.77
    已經
    2.67
    賅
    2.63
    鬭
    2.56
    sandalia
    2.53
    螄
    2.47
    祘
    2.45
    Activations Density 0.001%

    No Known Activations