© 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. 38234
    Prev
    Next
    INDEX
    Explanations

    Scripture Formatting

    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
     When
    -2.92
     unrelenting
    -2.89
     intricate
    -2.81
     unwavering
    -2.73
     Maybe
    -2.69
     innumerable
    -2.67
     garner
    -2.58
     exquisitely
    -2.56
     extraordinarily
    -2.56
     ALWAYS
    -2.56
    POSITIVE LOGITS
     erhi
    2.75
     gewi
    2.48
     somewhat
    2.47
     pivotal
    2.41
    และ
    2.41
    I
    2.39
     wonderfully
    2.38
     decidedly
    2.38
    ти
    2.36
     magnific
    2.36
    Activations Density 0.001%

    No Known Activations