© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13632
    Prev
    Next
    INDEX
    Explanations

    titles followed by specific entities

    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
     bross
    -1.32
     clô
    -1.28
     fré
    -1.25
    тельством
    -1.25
     rése
    -1.16
     parlament
    -1.16
     hant
    -1.16
     plafon
    -1.16
     ekolog
    -1.15
     véhic
    -1.14
    POSITIVE LOGITS
     will
    1.20
     absent
    0.97
     instig
    0.93
     paid
    0.91
    Bibliografie
    0.90
    0.90
     award
    0.89
     miesięcy
    0.88
    อย
    0.87
     Однако
    0.87
    Activations Density 0.221%

    No Known Activations