© 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. 2960
    Prev
    Next
    INDEX
    Explanations

    describing state or organization

    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
     usk
    1.46
     objek
    1.41
    魍
    1.38
    OMe
    1.33
    NQ
    1.32
    뮌
    1.31
     ук
    1.31
    Mve
    1.29
    ackbar
    1.29
     паў
    1.26
    POSITIVE LOGITS
     second
    0.94
     concurrent
    0.93
     Tweed
    0.93
    mselves
    0.92
    ̈
    0.90
    am
    0.89
     current
    0.88
     new
    0.88
    rames
    0.88
     first
    0.87
    Activations Density 0.035%

    No Known Activations