© 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. 122802
    Prev
    Next
    INDEX
    Explanations

    shopping bag

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

    optimizing, revolutionizing, maximizing

    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
     পরই
    0.53
    )».
    0.52
     rupani
    0.52
    :'],
    0.49
    すら
    0.49
    ਈ
    0.48
    ;'>
    0.48
     мэ
    0.48
    鏨
    0.48
    सूचित
    0.47
    POSITIVE LOGITS
    azada
    0.52
    y
    0.51
    bag
    0.50
     new
    0.49
    our
    0.48
    ley
    0.48
    á
    0.48
    jet
    0.47
     New
    0.47
     Bag
    0.46
    Activations Density 0.000%

    No Known Activations