© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3057
    Prev
    Next
    INDEX
    Explanations

    processing massive information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    ափ
    1.37
    締め
    1.37
    赚钱
    1.37
    að
    1.37
    гас
    1.36
     spéciale
    1.31
    цвет
    1.29
    쁨
    1.26
    vação
    1.25
    賺
    1.24
    POSITIVE LOGITS
    literature
    2.76
     literature
    2.68
     wikipedia
    2.52
     textbooks
    2.44
     scriptures
    2.37
     texts
    2.36
     Wikipedia
    2.29
     Scriptures
    2.28
     Literature
    2.25
     Textbook
    2.18
    Activations Density 0.757%

    No Known Activations