© 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. 66574
    Prev
    Next
    INDEX
    Explanations

    sudden changes or amounts

    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
     esclusivamente
    -1.28
    不是
    -1.20
    のように
    -1.19
     like
    -1.19
     hilft
    -1.18
     only
    -1.16
     elbise
    -1.16
    i
    -1.15
     dopln
    -1.15
    while
    -1.14
    POSITIVE LOGITS
    Etymology
    1.41
    ᐠ
    1.41
    )];
    1.38
    能在
    1.38
     comprender
    1.35
    nehå
    1.31
     alemanes
    1.30
    felizmente
    1.30
    身旁
    1.29
    Occasionally
    1.28
    Activations Density 0.112%

    No Known Activations