© 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. 173935
    Prev
    Next
    INDEX
    Explanations

    territories waiting

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

    foreign words and symbols

    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
    、、
    0.47
    q
    0.46
    :,
    0.45
     stratified
    0.44
    ras
    0.43
    espa
    0.43
    ^{
    0.43
    al
    0.42
    rían
    0.42
    诋
    0.42
    POSITIVE LOGITS
     बगल
    0.48
     gleiche
    0.46
    ポー
    0.46
    鬨
    0.46
    ジュール
    0.45
    ஜ்மஹால்
    0.45
     sympathize
    0.45
     vecin
    0.45
    verw
    0.45
     അവരുടെ
    0.44
    Activations Density 0.001%

    No Known Activations