© 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
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 4052
    Prev
    Next
    INDEX
    Explanations

    SQL FROM clause

    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
    ̛
    1.83
    drav
    1.81
     :=\
    1.78
     ~\
    1.73
    đenja
    1.69
    itzt
    1.67
     \,\
    1.66
     frameN
    1.66
     {}\
    1.66
    .'”
    1.63
    POSITIVE LOGITS
     Staten
    0.90
    antom
    0.87
     cardiaque
    0.80
    plots
    0.78
    ycl
    0.76
    ||
    0.74
    back
    0.74
     perf
    0.74
    perf
    0.73
    鉅
    0.72
    Activations Density 0.004%

    No Known Activations