© 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. 227397
    Prev
    Next
    INDEX
    Explanations

    religious holidays

    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
    for
    0.49
     замі
    0.49
    OCO
    0.49
    replaceAll
    0.46
    are
    0.46
    {
    0.46
    can
    0.46
    élim
    0.46
    und
    0.44
    the
    0.44
    POSITIVE LOGITS
     lengthening
    0.55
     отношения
    0.54
     elongated
    0.52
     ಅವರು
    0.50
     लटका
    0.50
     отношений
    0.48
    婀
    0.48
     सांप
    0.47
     घाटी
    0.47
     ayaa
    0.47
    Activations Density 0.000%

    No Known Activations