© 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. 22-GEMMASCOPE-RES-131K
    7. 15124
    Prev
    Next
    INDEX
    Explanations

    during or while

    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
    oughs
    -0.85
     sitten
    -0.84
    naje
    -0.82
     จาก
    -0.82
     obsah
    -0.81
     kaldı
    -0.81
    ardis
    -0.79
     הרבה
    -0.79
    purchased
    -0.79
    Endereço
    -0.77
    POSITIVE LOGITS
     during
    1.82
     while
    1.38
     durante
    1.32
     أثناء
    1.31
     während
    1.31
     podczas
    1.25
    During
    1.19
    embedded
    1.16
    DUR
    1.13
     During
    1.10
    Activations Density 0.111%

    No Known Activations