© 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. 39321
    Prev
    Next
    INDEX
    Explanations

    dataset benchmarks synthetic data

    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
     doing
    -1.60
     or
    -1.51
    olymers
    -1.46
     only
    -1.45
    yship
    -1.34
     necessary
    -1.33
     who
    -1.31
    这
    -1.30
     direction
    -1.30
     encuentras
    -1.30
    POSITIVE LOGITS
    任何人
    1.36
     pourront
    1.34
     recientemente
    1.30
     récemment
    1.28
     recentemente
    1.27
     RECENT
    1.23
     также
    1.21
    给大家
    1.21
    Occurs
    1.20
     UserName
    1.20
    Activations Density 0.144%

    No Known Activations