© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2942
    Prev
    Next
    INDEX
    Explanations

    explaining consequences or definitions

    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_15_width_16k_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
    aville
    1.50
     agendas
    1.48
     moods
    1.42
    Especially
    1.38
    只想
    1.35
    ropol
    1.33
    begin
    1.32
    <unused1797>
    1.32
     jangan
    1.31
    ounce
    1.30
    POSITIVE LOGITS
     equating
    1.70
    compared
    1.66
     compared
    1.63
    เทียบ
    1.58
    против
    1.50
    equivalent
    1.48
     implying
    1.45
    representing
    1.40
     مقارنه
    1.40
    对应
    1.37
    Activations Density 0.260%

    No Known Activations