© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6548
    Prev
    Next
    INDEX
    Explanations

    mathematical quantities like eigenvalues and mean

    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_12_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
     greco
    1.68
     Hyatt
    1.64
     mágico
    1.61
     Ally
    1.56
     EURO
    1.55
    ozy
    1.55
     Wonders
    1.54
    %{
    1.54
     Glow
    1.52
    greek
    1.51
    POSITIVE LOGITS
     $\
    1.16
    waste
    0.85
    <i>
    0.85
    uate
    0.83
    $\
    0.82
     cesse
    0.78
     waste
    0.74
    umsi
    0.72
     histogram
    0.72
     Sana
    0.71
    Activations Density 0.000%

    No Known Activations