© 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. 67404
    Prev
    Next
    INDEX
    Explanations

    Qt framework components

    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
     staunch
    -2.20
     Käufer
    -2.08
     other
    -2.02
     longtime
    -1.98
     wildly
    -1.97
     wholly
    -1.96
     our
    -1.95
     älskar
    -1.95
     their
    -1.94
     different
    -1.94
    POSITIVE LOGITS
    ཥ
    2.14
    (!__
    1.83
    に対して
    1.80
    toa
    1.77
     ila
    1.73
    :{
    1.72
    还没有
    1.70
    
    1.68
     solamente
    1.64
    бку
    1.63
    Activations Density 0.011%

    No Known Activations