© 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. 128548
    Prev
    Next
    INDEX
    Explanations

    obeyed, require, blockchain

    np_acts-logits-general · gemini-2.5-flash-lite

    finds function logic and descriptions

    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
     雨
    0.53
     পূর্ববাংলার
    0.51
    梆
    0.50
     guar
    0.49
    采访
    0.48
    蛲
    0.47
     skulls
    0.47
     музыки
    0.46
     పాల్
    0.46
     প্যার
    0.46
    POSITIVE LOGITS
    я
    0.52
    ू
    0.45
    ю
    0.44
    ul
    0.42
    у
    0.42
    ajax
    0.41
    वायु
    0.41
     y
    0.41
    নি
    0.41
     dominated
    0.40
    Activations Density 0.000%

    No Known Activations