© 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. 98340
    Prev
    Next
    INDEX
    Explanations

    demand for

    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
     höch
    -1.41
    hawatir
    -1.39
     impresiones
    -1.34
     búsquedas
    -1.31
    ,’
    -1.31
    大部分
    -1.29
     letzt
    -1.28
     intervenciones
    -1.27
     näher
    -1.27
     negociaciones
    -1.27
    POSITIVE LOGITS
     for
    2.47
    𝙨
    1.30
     tráiler
    1.30
     of
    1.29
    ради
    1.29
    っかけ
    1.27
     anadolu
    1.26
     by
    1.26
     demand
    1.25
    henden
    1.23
    Activations Density 0.016%

    No Known Activations