© 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. 33428
    Prev
    Next
    INDEX
    Explanations

    ROT13 cipher or code formatting

    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
     renderEncoder
    0.47
    лянчук
    0.47
    浐
    0.46
    স্ফ
    0.45
    Clientes
    0.44
    ামো
    0.44
     tamaños
    0.42
     extrémités
    0.42
    icketts
    0.42
     harmonique
    0.42
    POSITIVE LOGITS
     Hall
    0.54
     Bread
    0.52
     World
    0.51
     Skull
    0.51
     Joseph
    0.50
     Y
    0.49
     Q
    0.49
     G
    0.49
     Captain
    0.49
     David
    0.48
    Activations Density 0.008%

    No Known Activations