© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47245
    Prev
    Next
    INDEX
    Explanations

    while, contact, available, dreams, technology, yank

    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
     രോഗ
    0.50
     जिद
    0.46
     Erkrank
    0.45
    🤏
    0.44
     పరిష్
    0.43
     müssen
    0.43
     Два
    0.42
    糙
    0.42
    たり
    0.42
     Endangered
    0.41
    POSITIVE LOGITS
     shares
    0.47
     calendars
    0.44
    itz
    0.43
     utilizes
    0.41
     onboarding
    0.41
    のため
    0.41
     Latin
    0.39
     poetry
    0.39
    aundry
    0.39
     spreadsheets
    0.39
    Activations Density 0.003%

    No Known Activations