© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10210
    Prev
    Next
    INDEX
    Explanations

    one followed by society, culture, language, hand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ্ণ
    2.74
    া
    2.58
    ————————————————
    2.40
    ণের
    2.21
    as
    2.21
    ্ম্ম
    2.19
    أة
    2.18
    ിട
    2.16
    lat
    2.14
    าค
    2.13
    POSITIVE LOGITS
    蜮
    3.09
    באנגלית
    2.99
    ocyclic
    2.87
    <unused1217>
    2.86
     Tattha
    2.85
    SystemFileSystem
    2.85
     primarySwatch
    2.83
    inguished
    2.83
    ဉ
    2.77
    উন্ট
    2.76
    Activations Density 0.015%

    No Known Activations