© 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. 128207
    Prev
    Next
    INDEX
    Explanations

    programming utilities and selectors

    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
    ⤥
    -1.64
    ciech
    -1.56
    writerow
    -1.53
     =>
    -1.52
     Ubicación
    -1.51
    setopt
    -1.51
    Ї
    -1.51
    rounder
    -1.46
    🪟
    -1.45
    brainer
    -1.41
    POSITIVE LOGITS
     Perſ
    1.49
     Conſ
    1.47
     fameux
    1.46
    utiliz
    1.37
     ベルト
    1.35
     Inſ
    1.34
     coreana
    1.29
     solidif
    1.27
     alcune
    1.27
     debilit
    1.24
    Activations Density 0.013%

    No Known Activations