© 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. 9427
    Prev
    Next
    INDEX
    Explanations

    connecting related concepts or outcomes

    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
    嚭
    -1.22
    
    -1.20
     pittores
    -1.09
     Euró
    -1.09
     moza
    -1.09
     DÉ
    -1.09
     saus
    -1.09
     Italie
    -1.08
     RADIO
    -1.05
     pastillas
    -1.05
    POSITIVE LOGITS
     when
    1.27
     provide
    1.23
     during
    1.22
     as
    1.20
     make
    1.19
     change
    1.17
     develop
    1.09
     provides
    1.09
     big
    1.06
     give
    1.05
    Activations Density 0.053%

    No Known Activations