© 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. 10-GEMMASCOPE-RES-131K
    7. 59425
    Prev
    Next
    INDEX
    Explanations

    units, dates, months

    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
     since
    -1.80
     because
    -1.57
     exemplaires
    -1.32
     this
    -1.30
     than
    -1.27
     fubject
    -1.26
     cartier
    -1.24
     as
    -1.17
     sebag
    -1.17
     boîtier
    -1.16
    POSITIVE LOGITS
    いただけます
    1.48
     новым
    1.38
    ార
    1.29
    imetsu
    1.27
    Catégorie
    1.25
    。　　
    1.23
    getMenuInflater
    1.22
    .'
    1.22
    Beskrivelse
    1.20
    整个
    1.19
    Activations Density 0.072%

    No Known Activations