© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 27575
    Prev
    Next
    INDEX
    Explanations

    regular usage

    np_acts-logits-general · gemini-2.5-flash-lite

    regular followed by routines or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    0.79
    -
    0.78
    /
    0.77
    '
    0.75
    :
    0.71
     {
    0.64
    {
    0.63
     la
    0.60
    ");
    0.59
    <
    0.58
    POSITIVE LOGITS
    regular
    1.41
     नियमित
    1.22
     регуляр
    1.20
    Regular
    1.06
     regulares
    1.06
     régulière
    1.01
     regular
    1.00
     নিয়মিত
    0.99
     নিয়মিত
    0.93
     Regular
    0.93
    Activations Density 0.022%

    No Known Activations