© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13464
    Prev
    Next
    INDEX
    Explanations

    CFD Toolbox

    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
    {
    -3.83
     Если
    -2.50
    That
    -2.45
    Some
    -2.34
    l
    -2.33
    ra
    -2.33
    Many
    -2.31
    _
    -2.31
     это
    -2.30
     Have
    -2.30
    POSITIVE LOGITS
    歃
    3.69
    缯
    3.31
    镦
    3.19
    铩
    2.95
    艄
    2.89
     ferrovia
    2.86
    揠
    2.83
    屙
    2.78
    纡
    2.77
    ꦁ
    2.72
    Activations Density 0.031%

    No Known Activations