© 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. 21359
    Prev
    Next
    INDEX
    Explanations

    however, problem

    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
    [
    -3.48
    *
    -3.33
     it
    -2.72
    ,.
    -2.70
     then
    -2.61
    ),
    -2.55
    \\
    -2.48
    !
    -2.45
     da
    -2.31
    {
    -2.28
    POSITIVE LOGITS
    趼
    4.44
    塤
    3.48
    骝
    3.31
    婓
    3.08
    偁
    3.06
    
    2.97
    凩
    2.73
    あるので
    2.73
    茀
    2.69
    噐
    2.58
    Activations Density 0.001%

    No Known Activations