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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3746
    Prev
    Next
    INDEX
    Explanations

    leader, beacon, guardian, blade, example

    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
    パーツ
    1.63
     +-
    1.63
     meetup
    1.55
    취
    1.54
     Etsy
    1.54
     Buzz
    1.52
     Cosmetic
    1.51
    EEK
    1.51
     SoundCloud
    1.51
     MIDI
    1.51
    POSITIVE LOGITS
     sacrificed
    1.72
     voorbeeld
    1.57
    犧
    1.56
     sacr
    1.55
    esempio
    1.54
     exemplo
    1.52
     example
    1.52
     ejemplo
    1.51
     martyr
    1.46
     esempio
    1.44
    Activations Density 0.126%

    No Known Activations