© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 3708
    Prev
    Next
    INDEX
    Explanations

    code imports and graphics

    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
    s
    -1.56
    Its
    -1.45
    ate
    -1.38
     Of
    -1.37
    々木
    -1.35
    形式
    -1.35
     kupić
    -1.31
    ATE
    -1.30
     zarówno
    -1.30
    |()
    -1.30
    POSITIVE LOGITS
     varied
    1.63
     illustrating
    1.62
     to
    1.61
     vividly
    1.55
     increasingly
    1.53
    葙
    1.52
     ドラマ
    1.47
     decorada
    1.41
     of
    1.40
     proactively
    1.38
    Activations Density 0.001%

    No Known Activations