© 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. 15-GEMMASCOPE-2-RES-16K
    7. 6888
    Prev
    Next
    INDEX
    Explanations

    Make it / Make Ahead

    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
    мерикан
    1.39
    Hints
    1.38
     americanos
    1.31
    景象
    1.29
    锦
    1.28
    ليز
    1.27
    ccs
    1.27
    τι
    1.25
    ridor
    1.24
     питання
    1.23
    POSITIVE LOGITS
    adev
    1.33
    飲む
    1.11
    ェ
    1.10
     직선
    1.09
    otest
    1.08
    으니
    1.08
     (\"
    1.07
    ),\\
    1.05
     getActivity
    1.05
    candle
    1.05
    Activations Density 0.048%

    No Known Activations