© 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. 10-GEMMASCOPE-RES-131K
    7. 8057
    Prev
    Next
    INDEX
    Explanations

    names and businesses

    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
    in
    -1.20
    這些
    -1.17
     ersten
    -1.15
    for
    -1.14
     And
    -1.13
    These
    -1.13
     этих
    -1.12
    應用
    -1.11
    Estos
    -1.10
     esos
    -1.07
    POSITIVE LOGITS
     handels
    1.30
    anjutan
    1.28
     would
    1.16
    lieving
    1.16
    蔟
    1.15
    нент
    1.15
     comentarios
    1.14
    〙
    1.14
     deut
    1.13
     NATIONS
    1.13
    Activations Density 0.488%

    No Known Activations