© 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. 47327
    Prev
    Next
    INDEX
    Explanations

    surfaces and tabletops

    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
     hikes
    0.45
    itimes
    0.42
    穎
    0.42
     prosecutions
    0.41
    hiking
    0.38
    त्रियों
    0.38
     informed
    0.38
    Hiking
    0.38
     اعز
    0.38
    ꞌ
    0.38
    POSITIVE LOGITS
     tabletop
    0.70
    桌面
    0.67
    桌
    0.64
     tray
    0.63
     桌
    0.61
     trays
    0.59
     desktop
    0.58
     насто
    0.57
     টেব
    0.57
     centerpiece
    0.57
    Activations Density 0.063%

    No Known Activations