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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85030
    Prev
    Next
    INDEX
    Explanations

    car racing series and stakes

    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
     alemão
    -1.29
    rvore
    -1.28
    ська
    -1.27
    嬬
    -1.24
     dále
    -1.23
     feminina
    -1.23
     "@/
    -1.17
    ashqai
    -1.17
    してる
    -1.16
     spiega
    -1.16
    POSITIVE LOGITS
     our
    1.41
     your
    1.36
     merke
    1.32
    olphins
    1.23
    詛
    1.13
     on
    1.12
     pö
    1.12
     levert
    1.11
     you
    1.09
    DOUBLE
    1.09
    Activations Density 0.032%

    No Known Activations