© 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. 9236
    Prev
    Next
    INDEX
    Explanations

    names and initials

    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
    擽
    -2.06
    🫃
    -2.05
    recently
    -2.03
    previously
    -2.03
     meubles
    -2.00
    ≈
    -2.00
     Dinas
    -1.99
     vêtements
    -1.99
    
    -1.99
    
    -1.98
    POSITIVE LOGITS
     with
    3.06
     by
    2.83
     not
    2.73
     for
    2.72
     which
    2.69
     who
    2.66
     as
    2.61
     including
    2.55
     without
    2.55
     through
    2.42
    Activations Density 0.026%

    No Known Activations