© 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. 116562
    Prev
    Next
    INDEX
    Explanations

    by followed by a gerund or noun

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

    technical explanations and criteria

    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
    пи
    0.52
    פ
    0.48
    prism
    0.46
    Zed
    0.46
    -
    0.44
    plasma
    0.44
    order
    0.44
    thrust
    0.43
    L
    0.43
    penguin
    0.43
    POSITIVE LOGITS
    itattu
    0.56
    dır
    0.54
     ระ
    0.52
    되었
    0.52
    报考
    0.52
     indique
    0.51
     ถูก
    0.51
     advises
    0.50
     राशिफल
    0.50
     wurde
    0.50
    Activations Density 0.001%

    No Known Activations