© 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. 107850
    Prev
    Next
    INDEX
    Explanations

    section, tab, page, menu, list, panel

    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
    ισ
    -0.98
    는
    -0.96
     estudo
    -0.96
    Få
    -0.96
     сю
    -0.93
    Maar
    -0.93
    凄く
    -0.93
    tificate
    -0.91
    凄い
    -0.90
    ƣ
    -0.90
    POSITIVE LOGITS
     section
    3.59
     sections
    2.20
     area
    2.06
     tab
    1.95
     sección
    1.93
    section
    1.91
     portion
    1.88
     Section
    1.75
     page
    1.74
     bölüm
    1.52
    Activations Density 0.156%

    No Known Activations