© 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. 14951
    Prev
    Next
    INDEX
    Explanations

    court filings and appeals

    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
    ႐
    -1.99
    classed
    -1.86
    ;">
    -1.85
    
    -1.84
    rrrrrr
    -1.84
    [{{
    -1.80
    RRRR
    -1.78
    cmx
    -1.76
    floors
    -1.74
    ❣
    -1.74
    POSITIVE LOGITS
    p
    2.00
    d
    2.00
    l
    1.77
    E
    1.77
    5
    1.71
    ↵
    1.69
    太多的
    1.67
     
    1.62
    很好的
    1.57
    1
    1.56
    Activations Density 0.003%

    No Known Activations