© 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. 6252
    Prev
    Next
    INDEX
    Explanations

    yes I do

    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
    脛
    1.80
     oars
    1.77
    ҥ
    1.66
     бў
    1.65
    дә
    1.65
    胫
    1.64
     procéder
    1.64
    ργαν
    1.64
    เที่
    1.61
     strides
    1.60
    POSITIVE LOGITS
    level
    1.90
     level
    1.69
    /[
    1.58
     Level
    1.58
    /
    1.56
    Level
    1.55
    ynthia
    1.51
    enn
    1.49
    ドライ
    1.33
     TWO
    1.33
    Activations Density 0.001%

    No Known Activations