© 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. 34-GEMMASCOPE-RES-131K
    7. 81699
    Prev
    Next
    INDEX
    Explanations

    rolling and movement

    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_34/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
     LIND
    -0.77
     gantung
    -0.71
    σκευ
    -0.71
    новые
    -0.70
     Transplantation
    -0.68
     Bulgar
    -0.68
     perek
    -0.68
     Miroslav
    -0.66
    тят
    -0.66
    κολου
    -0.66
    POSITIVE LOGITS
     rolling
    5.78
     roll
    5.25
     rolled
    4.72
     Rolling
    4.63
     rolls
    4.63
    rolling
    4.59
    Rolling
    4.59
     Roll
    4.38
    roll
    4.31
    Roll
    4.31
    Activations Density 0.047%

    No Known Activations