© 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. 79628
    Prev
    Next
    INDEX
    Explanations

    statements following "is" or "should"

    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
     if
    -1.91
     before
    -1.70
     with
    -1.70
     during
    -1.63
     without
    -1.56
     while
    -1.55
     because
    -1.54
     unrelenting
    -1.51
     prevents
    -1.51
     from
    -1.48
    POSITIVE LOGITS
    somewhat
    1.75
    probably
    1.74
    actually
    1.70
     zoude
    1.70
    
    1.70
     strikingly
    1.70
     gewi
    1.68
     rajut
    1.67
    basically
    1.66
    鵙
    1.66
    Activations Density 0.076%

    No Known Activations