© 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. 43254
    Prev
    Next
    INDEX
    Explanations

    dates after "dated"

    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
    五年
    -1.78
    atrici
    -1.57
    他的
    -1.55
    屮
    -1.50
    また
    -1.45
    豋
    -1.45
    pulos
    -1.44
    itteet
    -1.44
    GORITHM
    -1.41
     if
    -1.41
    POSITIVE LOGITS
    1
    1.71
    —
    1.70
    \
    1.70
     yesterday
    1.55
    '
    1.53
     
    1.38
     kleineren
    1.34
     prides
    1.33
    eterangan
    1.31
     last
    1.30
    Activations Density 0.018%

    No Known Activations