© 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. 126609
    Prev
    Next
    INDEX
    Explanations

    Market Leader

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

    sentence fragments or common connectors

    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
     snuff
    0.48
    慗
    0.46
     watering
    0.46
    amer
    0.43
    净化
    0.43
     pressures
    0.42
    라는
    0.41
     sinking
    0.41
    交互
    0.41
    ดิจ
    0.40
    POSITIVE LOGITS
    a
    0.57
     {
    0.50
    قال
    0.48
     {//
    0.47
    Attempt
    0.45
     replete
    0.45
    legal
    0.45
     esfuer
    0.45
     オー
    0.44
    ા
    0.44
    Activations Density 0.000%

    No Known Activations