© 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. 99126
    Prev
    Next
    INDEX
    Explanations

    historic accommodations, luxury, friendly 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_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
     to
    -1.87
     encontraban
    -1.39
     querían
    -1.37
    licitations
    -1.31
     انسان
    -1.31
    还挺
    -1.31
     into
    -1.27
     its
    -1.27
    PKCS
    -1.27
    されていました
    -1.25
    POSITIVE LOGITS
     are
    1.50
     unsere
    1.41
     ‘’
    1.32
     dernière
    1.30
     autre
    1.29
     couldn
    1.27
    ↵↵
    1.27
     our
    1.26
     นิ้ว
    1.23
     must
    1.23
    Activations Density 0.142%

    No Known Activations