© 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. 79565
    Prev
    Next
    INDEX
    Explanations

    transition phrases

    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
     but
    -1.46
     lastly
    -1.09
    但是
    -1.07
    -------
    
    -1.06
     लेकिन
    -1.02
    ."/
    -1.02
     tapi
    -0.99
     män
    -0.96
     ();
    
    -0.96
    但
    -0.96
    POSITIVE LOGITS
     это
    1.20
    This
    1.11
    だけではなく
    1.09
     it
    1.09
    不僅
    1.07
    Moreover
    1.06
    不但
    1.03
    lanation
    1.02
    Furthermore
    1.02
     эту
    1.02
    Activations Density 0.217%

    No Known Activations