© 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. 129629
    Prev
    Next
    INDEX
    Explanations

    illustrations, stamp, flame

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

    Reduced tracking, ads struggle

    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
     कित
    0.47
     यकीन
    0.45
    🩰
    0.41
     antifungal
    0.40
     сним
    0.39
     photographs
    0.38
     &(
    0.38
     фотографи
    0.38
     tetrachloride
    0.38
     परे
    0.38
    POSITIVE LOGITS
    һ
    0.58
    neuron
    0.55
    忖
    0.52
     derog
    0.50
    azioni
    0.50
    수상
    0.48
    ადა
    0.48
    ાસ
    0.47
    raison
    0.47
    wirkung
    0.47
    Activations Density 0.000%

    No Known Activations