© 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. 141487
    Prev
    Next
    INDEX
    Explanations

    business and finance topics

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

    niche, competitors, and skepticism

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ato
    0.55
    cı
    0.51
    kład
    0.47
    Đ
    0.47
    A
    0.46
    约翰
    0.46
    ต์
    0.46
    ula
    0.45
    芰
    0.45
     sAlarm
    0.45
    POSITIVE LOGITS
     mercantile
    0.46
     troublesome
    0.46
     niche
    0.46
    طنين
    0.46
     immigrant
    0.45
     unscrupulous
    0.45
     extortion
    0.44
     wealthy
    0.44
     buying
    0.43
     menacing
    0.43
    Activations Density 0.001%

    No Known Activations