© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129200
    Prev
    Next
    INDEX
    Explanations

    calculating numbers and results

    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_22/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
    PDOException
    -1.02
    aminen
    -0.96
     to
    -0.96
    名称
    -0.96
    AMAHA
    -0.95
    bakken
    -0.93
     Niemand
    -0.92
    鈁
    -0.90
     кровать
    -0.89
    Faker
    -0.89
    POSITIVE LOGITS
     its
    1.29
     for
    1.29
     calculate
    1.26
     using
    1.21
     how
    1.18
     calculates
    1.11
     based
    1.10
     needed
    1.07
    calculate
    1.04
     if
    1.03
    Activations Density 0.102%

    No Known Activations