© 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. 40470
    Prev
    Next
    INDEX
    Explanations

    coding challenge sites

    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
     our
    -1.66
     or
    -1.54
     and
    -1.40
    できます
    -1.36
    f
    -1.27
    For
    -1.26
     unruly
    -1.23
     Traditionally
    -1.23
     in
    -1.20
     over
    -1.20
    POSITIVE LOGITS
     histoires
    1.55
     visiteurs
    1.55
     retours
    1.47
     reiter
    1.42
     gigantes
    1.41
     tendances
    1.41
     leçons
    1.41
    provides
    1.39
    Iam
    1.39
    Depends
    1.39
    Activations Density 0.040%

    No Known Activations