© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 23752
    Prev
    Next
    INDEX
    Explanations

    called "Basilica"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused338>
    0.50
    <unused311>
    0.48
    <unused323>
    0.47
    <unused301>
    0.47
    <unused706>
    0.46
    <unused2168>
    0.46
    <unused291>
    0.46
    brightness
    0.46
    <unused541>
    0.46
    <unused509>
    0.45
    POSITIVE LOGITS
     tzv
    0.62
     tzw
    0.58
     sogenannten
    0.55
     cosidd
    0.54
     sogenannte
    0.52
     sogen
    0.51
     called
    0.49
     Called
    0.43
     "
    0.43
     Basilica
    0.42
    Activations Density 0.179%

    No Known Activations