© 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. 176301
    Prev
    Next
    INDEX
    Explanations

    applied twice

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

    typical timeline

    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
    ﻨ
    0.59
    ಲ್ಯ
    0.48
    िसो
    0.47
    のかもし
    0.46
    િયાન
    0.45
    ilya
    0.45
    ILAR
    0.45
    ﻜ
    0.45
    يلة
    0.45
     hydrolyzed
    0.45
    POSITIVE LOGITS
     Utilizing
    0.50
     Initialization
    0.50
     Memory
    0.49
    el
    0.49
     Using
    0.49
     Custom
    0.49
     Initiative
    0.49
     Observed
    0.48
     Innovations
    0.47
     op
    0.47
    Activations Density 0.001%

    No Known Activations