© 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. 34-GEMMASCOPE-RES-131K
    7. 1157
    Prev
    Next
    INDEX
    Explanations

    on time

    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_34/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
    PN
    -0.88
    จาก
    -0.88
    ски
    -0.85
    news
    -0.83
    左
    -0.81
    Occurred
    -0.80
     Gruber
    -0.80
     śmierci
    -0.79
     dopiero
    -0.79
    После
    -0.78
    POSITIVE LOGITS
     timely
    2.58
     on
    2.16
     punct
    1.87
     đúng
    1.81
     Timely
    1.80
    timely
    1.77
     tepat
    1.71
     punctual
    1.69
     time
    1.59
     according
    1.41
    Activations Density 0.044%

    No Known Activations