© 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. 60970
    Prev
    Next
    INDEX
    Explanations

    for or "headline"

    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
    solicited
    -1.55
     is
    -1.46
    ?“
    -1.45
    饧
    -1.43
    ом
    -1.37
    succeeded
    -1.37
    Bets
    -1.35
    
    -1.35
     Laat
    -1.34
     Matte
    -1.32
    POSITIVE LOGITS
    where
    1.63
     which
    1.53
    Even
    1.51
    after
    1.49
    first
    1.49
     where
    1.49
     only
    1.48
    樁
    1.48
    這位
    1.48
    only
    1.45
    Activations Density 0.113%

    No Known Activations