© 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. 34-GEMMASCOPE-RES-131K
    7. 107226
    Prev
    Next
    INDEX
    Explanations

    function calls and object creation

    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
     courseId
    -1.02
    ac
    -1.02
    と共に
    -0.90
    -0.88
     neceff
    -0.87
    -0.87
    on
    -0.86
    ",&
    -0.85
    io
    -0.84
     The
    -0.84
    POSITIVE LOGITS
     komfort
    1.28
     lás
    1.11
     ilgi
    1.10
    kkor
    1.05
    elesaikan
    1.03
    konfirmasi
    1.02
     kré
    1.00
     komfor
    0.99
    zige
    0.99
    ÁR
    0.98
    Activations Density 0.034%

    No Known Activations