© 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. 39468
    Prev
    Next
    INDEX
    Explanations

    less than or equal to, greater than or equal to

    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
    (!__
    -1.21
    要么
    -1.03
    abriel
    -1.02
     juntamente
    -1.00
     mitge
    -1.00
     waarschijnlijk
    -1.00
     jestli
    -0.99
     eingeladen
    -0.99
     ¢
    -0.98
    
    -0.98
    POSITIVE LOGITS
     (
    1.31
     with
    1.29
     as
    1.06
     but
    1.04
     if
    1.02
    new
    1.02
    というか
    1.01
    سرائيل
    1.00
    impulan
    1.00
     Vielzahl
    0.98
    Activations Density 0.011%

    No Known Activations