© 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. 85666
    Prev
    Next
    INDEX
    Explanations

    Facebook Page

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

    is essential

    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
     la
    0.53
     även
    0.49
     både
    0.49
     و
    0.48
     è
    0.48
     &
    0.48
     د
    0.48
     bila
    0.47
     strum
    0.47
     also
    0.47
    POSITIVE LOGITS
    ড়ান্ত
    0.55
    inputSet
    0.54
    colorChoice
    0.51
    惘
    0.50
    displayed
    0.48
    쌉
    0.48
    ড়ান্ত
    0.48
    곶
    0.48
    createSprite
    0.47
    zinho
    0.47
    Activations Density 0.001%

    No Known Activations