© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5671
    Prev
    Next
    INDEX
    Explanations

    activities you enjoy

    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
     start
    1.44
     visor
    1.39
    始まる
    1.37
    鮪
    1.30
     regia
    1.29
     postfix
    1.29
     indiquée
    1.28
    ticker
    1.27
     unfolding
    1.26
    ********/
    1.26
    POSITIVE LOGITS
    aried
    1.57
    ensible
    1.55
    iquement
    1.55
    没事
    1.54
    away
    1.53
    érance
    1.47
     Kiya
    1.44
    katapos
    1.40
    zens
    1.37
    leys
    1.36
    Activations Density 0.028%

    No Known Activations