© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 168737
    Prev
    Next
    INDEX
    Explanations

    peculiar institution

    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
     I
    0.46
    ęcia
    0.45
    πλ
    0.43
    格
    0.41
    환
    0.41
    cmd
    0.40
    s
    0.40
    NOW
    0.39
    ورية
    0.39
    long
    0.39
    POSITIVE LOGITS
     UIS
    0.54
    榱
    0.54
     hervorrag
    0.53
     fuelwood
    0.49
    trashItem
    0.48
     ގ
    0.48
     achter
    0.47
     päiv
    0.47
     atthakath
    0.46
     Gubernur
    0.46
    Activations Density 0.002%

    No Known Activations