© 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. 34-GEMMASCOPE-RES-131K
    7. 48751
    Prev
    Next
    INDEX
    Explanations

    in its 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
     ظهر
    -0.80
     Ryzen
    -0.79
     Ведь
    -0.77
    obacz
    -0.77
    以来
    -0.75
     longues
    -0.75
     foglie
    -0.74
    langsung
    -0.72
    esi
    -0.71
    っぴ
    -0.71
    POSITIVE LOGITS
     due
    4.16
    due
    3.09
    Due
    3.03
     Due
    2.86
     debido
    2.48
     DUE
    2.44
     devido
    2.38
    DUE
    2.23
     time
    2.17
    由于
    1.97
    Activations Density 0.016%

    No Known Activations