© 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. 58472
    Prev
    Next
    INDEX
    Explanations

    describes circumstances or features

    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
     then
    -1.91
     also
    -1.84
    Тогда
    -1.63
    قرير
    -1.60
     opportunità
    -1.56
    Then
    -1.53
    During
    -1.52
     też
    -1.48
    سجيل
    -1.41
    غيير
    -1.41
    POSITIVE LOGITS
    currently
    1.46
     actuellement
    1.36
     deux
    1.33
    begin
    1.30
    unfortunately
    1.30
     sociala
    1.30
     senza
    1.29
    they
    1.27
    她和
    1.27
     мы
    1.25
    Activations Density 0.223%

    No Known Activations