© 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. 213257
    Prev
    Next
    INDEX
    Explanations

    academic and business content

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

    financial and shopping contexts

    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
     perfused
    0.46
    stdio
    0.45
     口
    0.42
     infar
    0.41
     homologs
    0.41
    JsonObject
    0.39
     ẞ
    0.39
    ครง
    0.39
     pathophysiology
    0.39
     publicKey
    0.39
    POSITIVE LOGITS
    Brands
    0.50
    Categ
    0.49
     акчага
    0.48
     Perspectives
    0.45
    เงิน
    0.45
    ྩ
    0.45
    ᙱ
    0.45
    網絡
    0.45
    Gmail
    0.44
     pursue
    0.44
    Activations Density 0.001%

    No Known Activations