© 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. 99813
    Prev
    Next
    INDEX
    Explanations

    court opinions and legal cases

    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
    -1.90
     was
    -1.77
     two
    -1.64
    i
    -1.59
     while
    -1.50
     through
    -1.45
     took
    -1.45
    C
    -1.42
     three
    -1.40
     although
    -1.39
    POSITIVE LOGITS
    すべての
    1.51
    这个
    1.40
    cannot
    1.38
    
    1.38
     男の子
    1.36
     zwierząt
    1.33
    abilities
    1.33
    这样的
    1.32
     escalier
    1.31
     اشار
    1.30
    Activations Density 0.149%

    No Known Activations