© 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. 184747
    Prev
    Next
    INDEX
    Explanations

    rabat.net addresses

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

    causes or effects

    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
     निरीक्षण
    0.50
     چند
    0.48
    繆
    0.48
     katol
    0.47
     दिनों
    0.46
     विभाजन
    0.46
     Tất
    0.46
    bedkar
    0.45
    јединачна
    0.45
     संक्रमण
    0.44
    POSITIVE LOGITS
    y
    0.54
    ✓
    0.48
    CA
    0.47
    PI
    0.46
    scott
    0.45
     yli
    0.45
     extraordin
    0.45
     at
    0.45
    Qty
    0.45
    d
    0.45
    Activations Density 0.001%

    No Known Activations