© 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. 69124
    Prev
    Next
    INDEX
    Explanations

    code identifiers and terminators

    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
     '
    -2.70
     of
    -2.56
     to
    -2.48
     
    -2.13
     never
    -1.98
     is
    -1.96
     in
    -1.96
     on
    -1.94
     won
    -1.94
     no
    -1.84
    POSITIVE LOGITS
    _
    3.14
    )
    2.84
    軼
    2.63
    tieth
    2.25
    I
    2.23
     xvi
    2.22
     Dicapai
    2.22
    毆
    2.20
    陝
    2.20
     OGSÅ
    2.20
    Activations Density 0.115%

    No Known Activations