© 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. 6610
    Prev
    Next
    INDEX
    Explanations

    brainfuck interpreter cells

    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
     হোমিওপ্যাথিক
    0.54
    customerId
    0.52
    revalidator
    0.52
    জ্জনক
    0.51
     srcset
    0.50
    ွဲ
    0.50
    แม
    0.49
    ǽ
    0.49
     koron
    0.49
    arranty
    0.48
    POSITIVE LOGITS
     Cell
    0.78
     Cells
    0.76
     cell
    0.74
    Cells
    0.69
    Cell
    0.69
     cells
    0.68
     Memory
    0.55
     Cellular
    0.55
     Unit
    0.55
     Sud
    0.55
    Activations Density 0.010%

    No Known Activations