© 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. 34-GEMMASCOPE-RES-131K
    7. 56993
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and divisions

    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_34/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
     phím
    -0.88
    激烈
    -0.81
    戦争
    -0.81
     Mädchen
    -0.79
    beten
    -0.77
    cador
    -0.75
    ־ה
    -0.74
    landes
    -0.73
     作品
    -0.73
    édric
    -0.73
    POSITIVE LOGITS
     graders
    1.21
     grader
    1.14
    degree
    1.08
    hand
    1.04
     baseman
    0.94
    arily
    0.94
     timers
    0.93
     食事
    0.84
    dup
    0.83
    meal
    0.83
    Activations Density 0.072%

    No Known Activations