© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 131487
    Prev
    Next
    INDEX
    Explanations

    rubik's cube, origami, folded paper

    np_acts-logits-general · gemini-2.5-flash-lite

    cube folding and manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sweeping
    0.43
    TAG
    0.39
    auction
    0.39
    დე
    0.39
    蒞
    0.39
     CALIFORNIA
    0.39
    ogas
    0.39
    vista
    0.39
    ব্য
    0.38
    掛
    0.38
    POSITIVE LOGITS
     Cube
    0.66
     cube
    0.59
    Cube
    0.54
     cubes
    0.53
     cubo
    0.50
    立方
    0.47
    CubeSize
    0.47
     Tetra
    0.46
     क्यूब
    0.46
    㓩
    0.45
    Activations Density 0.023%

    No Known Activations