© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43966
    Prev
    Next
    INDEX
    Explanations

    specific people and negative events

    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
    !”
    -3.56
    ，“
    -3.23
    、“
    -2.77
     (“
    -2.66
    。“
    -2.53
    ：“
    -2.47
     однако
    -2.42
     “
    -2.36
    ↑↑↑</
    -2.34
    姈
    -2.34
    POSITIVE LOGITS
    1
    2.77
    —
    2.70
    衚
    2.69
    [
    2.66
    Around
    2.56
    鋨
    2.55
    我的
    2.52
     lequel
    2.45
    鐿
    2.44
     valentín
    2.39
    Activations Density 0.005%

    No Known Activations