© 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. 93050
    Prev
    Next
    INDEX
    Explanations

    US sports teams and universities

    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
     there
    -1.40
     an
    -1.32
     from
    -1.26
     \
    -1.18
     by
    -1.16
    .......
    -1.13
     What
    -1.13
     tasty
    -1.12
     or
    -1.10
     !!!
    -1.09
    POSITIVE LOGITS
    去做
    1.16
    OOOO
    1.15
     rente
    1.13
     curent
    1.10
     corriger
    1.09
     dominante
    1.09
     beft
    1.09
     Dinas
    1.09
     utilisent
    1.07
     MICHAEL
    1.05
    Activations Density 0.069%

    No Known Activations