© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32139
    Prev
    Next
    INDEX
    Explanations

    product specifications, SKU, details

    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
    เพื่อน
    -1.03
    verture
    -0.82
     Sosial
    -0.81
     occafion
    -0.81
     Благо
    -0.80
    Ор
    -0.78
     Komunikasi
    -0.78
     białe
    -0.77
     hodně
    -0.77
    Контак
    -0.77
    POSITIVE LOGITS
    Please
    1.23
     warranty
    1.21
     SKU
    1.16
     Dimensions
    1.11
    PLEASE
    1.09
    sku
    1.06
     PLEASE
    1.06
     Please
    1.05
     sku
    1.05
     please
    1.03
    Activations Density 0.058%

    No Known Activations