© 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. 75727
    Prev
    Next
    INDEX
    Explanations

    International Capital Markets

    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
     podría
    0.44
     Ticket
    0.41
     Else
    0.40
     Painting
    0.40
    pbs
    0.39
     Modern
    0.39
     உங்களுக்கு
    0.39
     |
    0.38
     Skipper
    0.38
     Scheduler
    0.38
    POSITIVE LOGITS
    背面
    0.44
    ClNO
    0.44
    وني
    0.43
    クトル
    0.43
    尻
    0.43
    فا
    0.43
    員
    0.43
    旁邊
    0.42
     アー
    0.42
     ক্রমা
    0.42
    Activations Density 0.005%

    No Known Activations