© 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. 31-GEMMASCOPE-2-RES-262K
    7. 19243
    Prev
    Next
    INDEX
    Explanations

    finding simple patterns

    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/layer_31_width_262k_l0_medium
    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
    <unused23>
    0.52
    า
    0.51
    ʬ
    0.50
    𝐂
    0.50
    icherheit
    0.49
     इलेक्ट्रॉनिक
    0.49
    梩
    0.49
     jego
    0.48
    <unused250>
    0.48
    镍
    0.48
    POSITIVE LOGITS
     Qu
    0.44
     Maintain
    0.43
     Hid
    0.42
    وب
    0.42
     maintain
    0.40
     isolating
    0.39
     Recognize
    0.38
     sharing
    0.37
     L
    0.37
     maintaining
    0.36
    Activations Density 0.001%

    No Known Activations