© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13154
    Prev
    Next
    INDEX
    Explanations

    identified factors and domains

    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
     acheter
    -1.25
     entré
    -1.24
     dieu
    -1.21
     raiſ
    -1.21
     bébé
    -1.21
     joli
    -1.20
    粜
    -1.16
     vedette
    -1.14
     politik
    -1.13
     zéro
    -1.13
    POSITIVE LOGITS
     on
    1.23
     now
    1.11
     when
    1.09
    hatenablog
    1.08
    figcaption
    1.05
     would
    1.05
     at
    1.02
    这些
    1.00
    velocityX
    0.98
     will
    0.97
    Activations Density 0.035%

    No Known Activations