© 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-16K
    7. 5500
    Prev
    Next
    INDEX
    Explanations

    miniature golf and bowling

    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_16k_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
    ≜
    0.49
     Опера
    0.47
    忻
    0.46
     SimSun
    0.45
    講演
    0.45
    ⊷
    0.45
     రచ
    0.44
     السياسي
    0.44
     nihil
    0.44
    オペ
    0.44
    POSITIVE LOGITS
     golf
    1.81
    Golf
    1.66
     Golf
    1.59
     golfers
    1.58
     golfing
    1.52
    golf
    1.52
     golfer
    1.48
    ゴルフ
    1.36
    🏌
    1.34
     ゴルフ
    1.33
    Activations Density 0.063%

    No Known Activations