© 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. 72633
    Prev
    Next
    INDEX
    Explanations

    time durations and units

    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
    each
    -1.11
    シンプル
    -1.03
     each
    -1.03
     FATHER
    -1.03
     accett
    -0.99
    s
    -0.99
     richi
    -0.98
    áles
    -0.97
     riemp
    -0.97
    While
    -0.97
    POSITIVE LOGITS
     ändå
    1.17
    apimachinery
    1.16
     olika
    1.14
    芙
    1.09
    ',
    1.09
     omfatt
    1.07
    yaç
    1.05
     verkligen
    1.05
     összefoglal
    1.05
     ganska
    1.03
    Activations Density 0.013%

    No Known Activations