© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85783
    Prev
    Next
    INDEX
    Explanations

    Thomas Chapin

    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
    i
    -1.53
     we
    -1.50
     kateg
    -1.38
    ي
    -1.35
     Dalam
    -1.34
    ца
    -1.32
     şark
    -1.29
     Career
    -1.24
     uhr
    -1.23
     francia
    -1.23
    POSITIVE LOGITS
    特に
    1.63
    もともと
    1.55
    新しく
    1.43
     ursprüng
    1.38
    especially
    1.36
    dersfield
    1.35
     особенно
    1.34
    Pratique
    1.33
    即便是
    1.32
     vorhand
    1.30
    Activations Density 0.008%

    No Known Activations