© 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. 9452
    Prev
    Next
    INDEX
    Explanations

    or and and with quotes

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

    items separated by commas or 'or'

    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
     Local
    0.50
     stora
    0.50
     chirop
    0.49
    <unused1844>
    0.47
     gyakor
    0.47
     spacetime
    0.46
     প্রথমেই
    0.46
     utili
    0.46
    <unused1857>
    0.46
     deles
    0.46
    POSITIVE LOGITS
     “‘
    1.26
     "'
    1.08
    「
    1.08
     "\"
    0.94
     %``
    0.94
     “(
    0.94
     "¿
    0.93
     “
    0.92
     “[
    0.91
     "
    0.91
    Activations Density 0.133%

    No Known Activations