© 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. 72116
    Prev
    Next
    INDEX
    Explanations

    jigsaw puzzles and crosswords

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

    puzzles and jigsaws

    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
    ess
    0.50
    payment
    0.48
    sion
    0.46
    ession
    0.46
    faculty
    0.45
    ste
    0.45
    频
    0.44
    receipt
    0.44
    kart
    0.43
    tax
    0.43
    POSITIVE LOGITS
     puzzles
    0.76
     puzzle
    0.72
     पजल
    0.70
     Puzzle
    0.65
    🧩
    0.61
     intricately
    0.59
     Giải
    0.59
     しっかり
    0.59
     Erfahrung
    0.59
     Vorder
    0.59
    Activations Density 0.025%

    No Known Activations