© 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. 40813
    Prev
    Next
    INDEX
    Explanations

    shortcut icon

    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
     gewi
    -1.60
     acht
    -1.59
     trois
    -1.55
    adalah
    -1.55
     lác
    -1.53
     heilig
    -1.45
    heir
    -1.41
    aaaaaa
    -1.39
    became
    -1.38
    uuuu
    -1.38
    POSITIVE LOGITS
     with
    2.20
     like
    1.77
     described
    1.63
     through
    1.62
     has
    1.61
     while
    1.57
     mainly
    1.55
    这下
    1.54
     directly
    1.53
     would
    1.49
    Activations Density 0.135%

    No Known Activations