© 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. 67860
    Prev
    Next
    INDEX
    Explanations

    static declarations

    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
    pentru
    -1.89
     konkuren
    -1.88
    
    -1.84
     celebró
    -1.84
     rémun
    -1.80
     dát
    -1.78
    絎
    -1.77
     aveva
    -1.73
    
    -1.73
    蹰
    -1.73
    POSITIVE LOGITS
    ”
    2.50
     from
    2.09
    0
    1.98
    ”,
    1.91
    i
    1.88
    4
    1.88
     as
    1.87
     despite
    1.86
     people
    1.83
     demonstrates
    1.77
    Activations Density 0.006%

    No Known Activations