© 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. 201424
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
     rins
    0.45
     ла
    0.41
     analyse
    0.39
     /
    0.39
     tests
    0.39
     textbox
    0.39
     balances
    0.39
     Beatles
    0.39
     Analyzing
    0.39
     control
    0.38
    POSITIVE LOGITS
    partite
    0.48
    Constitution
    0.48
     ಅವಕಾಶ
    0.46
    宪
    0.41
     ہاکی
    0.39
    وسیع
    0.39
    ITTER
    0.38
    voren
    0.38
     لوبه
    0.37
    മി
    0.37
    Activations Density 0.028%

    No Known Activations