© 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. 128726
    Prev
    Next
    INDEX
    Explanations

    providing help

    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
    -1.68
     or
    -1.51
    豨
    -1.43
        
    -1.34
    вля
    -1.30
     using
    -1.29
    赑
    -1.27
    原来
    -1.24
    邻居
    -1.23
    ख्य
    -1.20
    POSITIVE LOGITS
     patients
    1.83
     you
    1.82
     разные
    1.72
     samego
    1.69
    useNewUrlParser
    1.66
    能夠
    1.60
     Sosial
    1.60
    槻
    1.58
    能够
    1.56
     Siehe
    1.56
    Activations Density 0.032%

    No Known Activations