© 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. 102544
    Prev
    Next
    INDEX
    Explanations

    puis then is ?

    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
    These
    -1.70
     akrab
    -1.49
     burbujas
    -1.47
     tyto
    -1.43
    這些
    -1.42
     醬
    -1.42
    Those
    -1.41
    ınıza
    -1.40
    liyor
    -1.38
     salonu
    -1.37
    POSITIVE LOGITS
     then
    1.80
    </td>
    1.50
     puis
    1.32
     in
    1.30
    ?
    1.27
    *
    1.24
    𝟑
    1.20
     is
    1.17
    RTLR
    1.16
    ooplankton
    1.16
    Activations Density 0.177%

    No Known Activations