© 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. 10-GEMMASCOPE-RES-131K
    7. 47779
    Prev
    Next
    INDEX
    Explanations

    politician party and state abbreviations

    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
     in
    -2.53
    ;
    -2.33
     both
    -2.13
     any
    -2.09
     two
    -2.08
     even
    -1.90
     more
    -1.88
    ."
    -1.87
    .”
    -1.86
    ?
    -1.84
    POSITIVE LOGITS
    岽
    1.73
     sê
    1.72
     soooo
    1.66
     sommige
    1.63
     trám
    1.61
    inige
    1.58
    鶫
    1.58
     sooo
    1.56
     partici
    1.56
     tê
    1.55
    Activations Density 0.040%

    No Known Activations