© 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. 238395
    Prev
    Next
    INDEX
    Explanations

    property and citizens

    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
    StillWater
    0.54
     Realtors
    0.52
    棪
    0.52
     Realty
    0.50
     detrimental
    0.48
    हली
    0.47
     tolerances
    0.47
     Worry
    0.46
     Είναι
    0.45
    燹
    0.45
    POSITIVE LOGITS
    via
    0.51
    Through
    0.47
    Via
    0.47
     באמצעות
    0.45
    <0xE2>
    0.45
    <0xE3>
    0.45
    \
    0.44
    about
    0.43
    begin
    0.43
     mediante
    0.43
    Activations Density 0.000%

    No Known Activations