© 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. 82877
    Prev
    Next
    INDEX
    Explanations

    database structure and definitions

    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
    장이
    0.47
     begg
    0.44
     nondestructive
    0.44
     anecd
    0.43
    শস্ত্র
    0.43
    ￫
    0.43
    норийска
    0.43
    پ
    0.43
    ༞
    0.42
    기와
    0.42
    POSITIVE LOGITS
     erklärte
    0.53
     zegt
    0.50
     sagt
    0.49
     erklärt
    0.49
     ഗു
    0.46
     Bürgermeister
    0.45
     stale
    0.44
     Hak
    0.44
     በላይ
    0.44
     řek
    0.43
    Activations Density 0.000%

    No Known Activations