© 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. 71954
    Prev
    Next
    INDEX
    Explanations

    ending code statements

    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
    Not in Any Lists

    No Comments

    Negative Logits
     gewi
    -1.92
     Dinas
    -1.88
    蛲
    -1.78
    颪
    -1.74
     diversos
    -1.63
    ⩕
    -1.62
    鲩
    -1.61
    dicionado
    -1.60
     cette
    -1.60
     WIL
    -1.57
    POSITIVE LOGITS
    3
    1.71
     continual
    1.64
    1
    1.63
     plethora
    1.58
    Pener
    1.58
    2
    1.54
    Tentang
    1.53
     extraordinarily
    1.52
     horrific
    1.52
    4
    1.51
    Activations Density 0.166%

    No Known Activations