© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3867
    Prev
    Next
    INDEX
    Explanations

    mutable data structures

    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
    _
    -2.13
    /
    -1.51
            
    -1.45
     of
    -1.33
    G
    -1.32
     sepen
    -1.32
     a
    -1.32
    B
    -1.30
    V
    -1.27
     asli
    -1.25
    POSITIVE LOGITS
    zionali
    1.55
    siasme
    1.49
    ’?
    1.40
    狲
    1.39
    金币
    1.35
    uevos
    1.34
     These
    1.34
    embley
    1.31
    čky
    1.30
     ballpark
    1.29
    Activations Density 0.017%

    No Known Activations