© 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. 40342
    Prev
    Next
    INDEX
    Explanations

    diamond rings, hotel, island, tip, gang saw

    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
    ↵
    -3.28
    on
    -2.94
     -
    -2.64
    or
    -2.45
    an
    -2.41
    );
    -2.38
    .'
    -2.36
     essas
    -2.34
    ak
    -2.28
     somewhat
    -2.27
    POSITIVE LOGITS
    鋱
    2.91
     respekt
    2.67
    
    2.63
    蹌
    2.59
    驺
    2.39
     и
    2.34
     pedimos
    2.31
     silencioso
    2.27
     și
    2.27
     groupe
    2.25
    Activations Density 0.018%

    No Known Activations