© 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. 40771
    Prev
    Next
    INDEX
    Explanations

    food and tasting events

    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
     that
    -2.02
     it
    -1.90
     when
    -1.62
     because
    -1.60
     this
    -1.58
     in
    -1.44
     which
    -1.44
     you
    -1.40
    When
    -1.32
     after
    -1.30
    POSITIVE LOGITS
     evtl
    1.47
     will
    1.30
     μόνο
    1.30
     parmi
    1.25
     similaire
    1.21
     pourront
    1.21
     canadi
    1.21
    mainloop
    1.17
    possibly
    1.16
    ViewChild
    1.16
    Activations Density 0.096%

    No Known Activations