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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39007
    Prev
    Next
    INDEX
    Explanations

    specific locations and times

    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
     for
    -1.73
     by
    -1.53
     would
    -1.40
     like
    -1.33
     is
    -1.30
    4
    -1.27
     should
    -1.26
     all
    -1.23
     with
    -1.23
     in
    -1.20
    POSITIVE LOGITS
    unno
    1.52
     about
    1.43
     ビキニ
    1.36
    carus
    1.36
    
    1.30
    
    1.27
    ruka
    1.26
    翃
    1.23
    izate
    1.23
     årets
    1.23
    Activations Density 0.155%

    No Known Activations