© 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. 7737
    Prev
    Next
    INDEX
    Explanations

    programming code and structures

    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
     هایی
    -2.00
     szczeg
    -1.70
    _{
    -1.63
    langsung
    -1.60
    caucasian
    -1.59
     cinturón
    -1.53
     двумя
    -1.52
     But
    -1.51
    ‌های
    -1.50
     sosteniendo
    -1.49
    POSITIVE LOGITS
    牁
    1.79
    se
    1.77
    魔兽
    1.62
    citement
    1.61
    woman
    1.60
     aſ
    1.59
     GARANT
    1.55
    timation
    1.54
    ductors
    1.52
     COMMERCE
    1.52
    Activations Density 0.033%

    No Known Activations