© 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. 75512
    Prev
    Next
    INDEX
    Explanations

    specific subsequent words

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

    special characters 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
    يك
    0.62
    يد
    0.55
    كر
    0.53
    يذ
    0.52
    وم
    0.52
    ير
    0.51
    يل
    0.51
    맟
    0.51
    يت
    0.50
    ایت
    0.50
    POSITIVE LOGITS
    pn
    0.68
     demon
    0.55
    moment
    0.52
    lama
    0.51
     Screening
    0.50
    weisen
    0.50
     transient
    0.49
     बदलाव
    0.49
    pod
    0.49
    pio
    0.48
    Activations Density 0.000%

    No Known Activations