© 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. 21315
    Prev
    Next
    INDEX
    Explanations

    multilingual contexts

    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
     عندما
    -1.65
    karena
    -1.46
     porque
    -1.46
    cuando
    -1.41
     cosas
    -1.38
     escrito
    -1.38
     cuando
    -1.38
     vieja
    -1.36
     quando
    -1.34
     justo
    -1.34
    POSITIVE LOGITS
     your
    2.09
     this
    2.02
     such
    1.57
     these
    1.55
     murieron
    1.44
     to
    1.41
     according
    1.40
     each
    1.38
    ítés
    1.33
    ければ
    1.27
    Activations Density 0.026%

    No Known Activations