© 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. 34-GEMMASCOPE-RES-131K
    7. 63416
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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_34/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
    際には
    -1.40
    になってしまう
    -1.30
     bébés
    -1.26
    際は
    -1.25
     испан
    -1.18
    たびに
    -1.14
    慣れて
    -1.14
     vivent
    -1.09
     viață
    -1.09
    votre
    -1.08
    POSITIVE LOGITS
     how
    2.36
     Why
    2.27
     Does
    2.23
     How
    2.16
     why
    2.09
     What
    2.08
     the
    1.97
     what
    1.83
     From
    1.78
     Is
    1.77
    Activations Density 0.090%

    No Known Activations