© 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. 103600
    Prev
    Next
    INDEX
    Explanations

    time passed or passing

    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
    觔
    -1.93
    目前的
    -1.68
    !’
    -1.66
     rotu
    -1.66
    two
    -1.63
     shown
    -1.59
     desti
    -1.57
    OUTUBE
    -1.56
     vias
    -1.55
    を見せて
    -1.55
    POSITIVE LOGITS
     که
    1.66
    这
    1.60
     that
    1.54
    你
    1.54
     penyanyi
    1.53
     "..\..\..\
    1.48
     Ирина
    1.45
    檢查
    1.45
     which
    1.42
     tenté
    1.42
    Activations Density 0.004%

    No Known Activations