© 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. 44717
    Prev
    Next
    INDEX
    Explanations

    articles and quantifiers followed by nouns

    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
     of
    -1.39
    inawa
    -1.39
     because
    -1.33
    Hechos
    -1.30
     themselves
    -1.30
     GreatSchools
    -1.27
     protože
    -1.25
     cenderung
    -1.23
     justru
    -1.22
     Họ
    -1.22
    POSITIVE LOGITS
    憷
    1.63
     trouxe
    1.61
    ↵
    1.52
    pergillus
    1.50
    مان
    1.38
    "
    1.34
    randa
    1.33
    eloma
    1.30
    ymmetry
    1.30
     ofreci
    1.27
    Activations Density 0.016%

    No Known Activations