© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200227
    Prev
    Next
    INDEX
    Explanations

    wheel or cuts

    np_acts-logits-general · gemini-2.5-flash-lite

    machine learning models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ინი
    0.48
     réussite
    0.48
    渽
    0.46
    คนที่
    0.46
    の人
    0.46
     розвитку
    0.45
     decyz
    0.45
    貢献
    0.45
     diversité
    0.45
    トゥーン
    0.45
    POSITIVE LOGITS
    max
    0.63
     or
    0.62
    f
    0.61
    shape
    0.61
    )+
    0.60
    ford
    0.60
    hanging
    0.59
    axis
    0.58
    或
    0.57
    empty
    0.56
    Activations Density 0.004%

    No Known Activations