© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 183247
    Prev
    Next
    INDEX
    Explanations

    waste materials

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

    Egg Stage

    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
    Negative Logits
     low
    0.54
     release
    0.52
     (
    0.51
    RELEASE
    0.51
     water
    0.51
     RELEASE
    0.51
     expressive
    0.50
     place
    0.49
     Poole
    0.49
     down
    0.49
    POSITIVE LOGITS
    予以
    0.49
    AIRMAN
    0.48
     сохрани
    0.44
     QuantityOnHand
    0.44
    spaper
    0.43
     }{}_{\
    0.43
     கொடுத்து
    0.43
    icator
    0.43
     парла
    0.43
     депутат
    0.43
    Activations Density 0.003%

    No Known Activations