© 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. 43060
    Prev
    Next
    INDEX
    Explanations

    standards and limits

    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
     Inſ
    -1.52
    蛱
    -1.34
     dehors
    -1.32
     Eſ
    -1.31
    骉
    -1.28
    timme
    -1.28
    peño
    -1.28
    cetes
    -1.27
     internes
    -1.26
     assurent
    -1.26
    POSITIVE LOGITS
     for
    1.70
     they
    1.49
     by
    1.42
     requirements
    1.30
     you
    1.30
     says
    1.29
     criteria
    1.25
     guidelines
    1.25
     Tuesday
    1.23
    ulgação
    1.20
    Activations Density 0.061%

    No Known Activations