© 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. 127783
    Prev
    Next
    INDEX
    Explanations

    events and circumstances

    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
     our
    -2.05
     for
    -1.66
     we
    -1.54
     solchen
    -1.40
     someone
    -1.33
     similar
    -1.30
    嗌
    -1.28
     Mère
    -1.27
     others
    -1.23
     ourselves
    -1.23
    POSITIVE LOGITS
     alre
    1.41
     spru
    1.30
    āju
    1.29
     REVOL
    1.25
    とはいえ
    1.25
     メニュー
    1.25
    镰
    1.21
     conno
    1.19
    トゥ
    1.18
    弹窗
    1.18
    Activations Density 0.404%

    No Known Activations