© 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. 12954
    Prev
    Next
    INDEX
    Explanations

    age and height restrictions

    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
     Weiterbildung
    -0.98
     Prevent
    -0.93
     quickly
    -0.91
     new
    -0.90
     what
    -0.88
     लोगों
    -0.87
    IZONTAL
    -0.87
    美丽的
    -0.85
     was
    -0.84
     name
    -0.84
    POSITIVE LOGITS
     berpeng
    1.16
     osallist
    1.13
     children
    1.04
     getChild
    1.00
     Erkrankung
    1.00
     youngster
    0.99
     polvere
    0.99
     déplacements
    0.98
    ENDPOINT
    0.98
    enação
    0.98
    Activations Density 0.009%

    No Known Activations