© 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. 166819
    Prev
    Next
    INDEX
    Explanations

    game mechanics

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

    `flag`, `dance classes`, `vulnerability`, `payment based`

    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
    윗
    0.47
     ha
    0.46
    상의
    0.45
     basilica
    0.44
    oba
    0.43
     wheat
    0.43
    ugas
    0.42
    상이
    0.42
    Türkiye
    0.42
    ㅏ
    0.41
    POSITIVE LOGITS
    aprendizaje
    0.52
     aprend
    0.49
     réd
    0.48
    ratto
    0.47
     периода
    0.47
     fonbet
    0.46
     لينك
    0.46
    ﺗ
    0.46
    ဆုံး
    0.45
    rard
    0.45
    Activations Density 0.001%

    No Known Activations