© 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. 75803
    Prev
    Next
    INDEX
    Explanations

    previously acquired life been that rocks is applied no

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

    price war

    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
    econom
    0.58
     financially
    0.55
     econom
    0.54
     अधिकांश
    0.54
     economically
    0.52
     ar
    0.51
     v
    0.49
     weather
    0.48
     finan
    0.48
     subsid
    0.48
    POSITIVE LOGITS
    кову
    0.55
    尼斯
    0.53
    цкі
    0.53
    蘖
    0.51
    Malformed
    0.50
    ці
    0.50
    స్కీ
    0.50
    ้า
    0.50
    кса
    0.50
    田
    0.50
    Activations Density 0.002%

    No Known Activations