© 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. 135236
    Prev
    Next
    INDEX
    Explanations

    colorless, brown, coloring

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

    completion or optional steps

    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
    ාව
    0.54
    탰
    0.54
     আসলে
    0.48
    ड़ब
    0.48
     içer
    0.47
    쩝
    0.47
     જાણ
    0.47
     यू
    0.46
    案例
    0.46
     بھول
    0.46
    POSITIVE LOGITS
     coloring
    0.55
     carving
    0.50
     {
    0.48
     crispy
    0.48
     +
    0.47
    ius
    0.47
     poisoning
    0.47
     brown
    0.46
     colouring
    0.46
     colorless
    0.46
    Activations Density 0.001%

    No Known Activations