© 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. 82696
    Prev
    Next
    INDEX
    Explanations

    local events and specific topics

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

    describing current state or recent past

    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
    к
    0.52
    त
    0.50
     газе
    0.50
     газа
    0.50
    ك
    0.49
    зной
    0.48
     нарушения
    0.48
    ज
    0.48
    ф
    0.47
    ेंट
    0.46
    POSITIVE LOGITS
    highlight
    0.46
     muttered
    0.46
    Packed
    0.44
     vast
    0.43
     towering
    0.42
     secluded
    0.42
     Tope
    0.42
     backdrop
    0.42
     erythro
    0.41
     Ljublj
    0.41
    Activations Density 0.000%

    No Known Activations