© 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. 99851
    Prev
    Next
    INDEX
    Explanations

    carrying items in bags

    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
    0
    -2.03
    鄚
    -1.62
    in
    -1.59
    writing
    -1.50
    so
    -1.47
    although
    -1.36
     conscientious
    -1.36
    i
    -1.35
     приходится
    -1.33
     IBOutlet
    -1.33
    POSITIVE LOGITS
     almac
    1.53
     entendimiento
    1.52
     conveyed
    1.50
     レース
    1.48
     ‘‘
    1.46
    يمق
    1.45
     admiten
    1.43
     ejerc
    1.41
    あれば
    1.40
     égale
    1.37
    Activations Density 0.010%

    No Known Activations