© 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. 22-GEMMASCOPE-RES-131K
    7. 34859
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and derivations

    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_22/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
    ♲
    -1.38
     praticamente
    -1.36
     specif
    -1.36
    摀
    -1.34
     captivating
    -1.33
     verschillende
    -1.31
    referred
    -1.27
    蛲
    -1.27
     dó
    -1.27
     ſever
    -1.27
    POSITIVE LOGITS
     with
    2.11
     only
    1.86
     again
    1.84
     Since
    1.81
     since
    1.76
     while
    1.66
     now
    1.65
     because
    1.62
     after
    1.55
     through
    1.55
    Activations Density 0.009%

    No Known Activations