© 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. 40-GEMMASCOPE-2-RES-262K
    4. 166530
    Prev
    Next
    INDEX
    Explanations

    golf game types

    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_40_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
     drivers
    0.45
    ⊟
    0.40
     kub
    0.37
     世
    0.37
     Klim
    0.36
    Drivers
    0.36
     Wedge
    0.36
    世
    0.36
    ⊢
    0.35
     BOX
    0.35
    POSITIVE LOGITS
    resolve
    0.46
     cheque
    0.44
     جیت
    0.43
     kemenangan
    0.43
    淍
    0.43
     দোয়া
    0.42
     पेमेंट
    0.41
    在哪里
    0.40
     fist
    0.40
    Landau
    0.40
    Activations Density 0.003%

    No Known Activations