© 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. 51763
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Sci
    0.50
    Denne
    0.45
    ዴ
    0.44
    worst
    0.44
    ocz
    0.43
    σι
    0.43
    Worst
    0.43
     minDist
    0.43
    Mitchell
    0.43
    Mercedes
    0.43
    POSITIVE LOGITS
     Known
    0.51
     不要
    0.50
     程序
    0.50
     Thought
    0.49
     معك
    0.47
     神
    0.47
     Kingdoms
    0.47
     Former
    0.46
     Anzeigen
    0.46
     Shaped
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.