© 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. 2122
    Prev
    Next
    INDEX
    Explanations

    python code requests

    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
     trough
    0.91
    )^{
    0.89
    arded
    0.85
     berbahaya
    0.85
    )}^{
    0.83
    amentul
    0.82
    })^{
    0.80
    adura
    0.79
    uración
    0.79
    いいね
    0.78
    POSITIVE LOGITS
    Произ
    1.58
     劉
    1.33
    Чи
    1.32
    frequency
    1.31
    ratio
    1.31
     Masai
    1.28
     خلق
    1.28
     сколько
    1.28
    Ratio
    1.27
     príp
    1.23
    Activations Density 0.150%

    No Known Activations