© 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. 128898
    Prev
    Next
    INDEX
    Explanations

    elem, evaluable

    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
    ’
    -3.25
     ―
    -2.89
     The
    -2.88
    ).
    -2.86
    an
    -2.75
    }
    -2.61
    you
    -2.56
     You
    -2.45
    ");
    -2.38
     shenanigans
    -2.36
    POSITIVE LOGITS
    鯔
    3.02
    龵
    3.00
    geſ
    2.94
    ۉ
    2.92
    汌
    2.78
    ༑
    2.77
    鯢
    2.73
    ଝ
    2.66
    鹀
    2.63
    
    2.56
    Activations Density 0.001%

    No Known Activations