© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2218
    Prev
    Next
    INDEX
    Explanations

    puzzle solving game

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

    The neuron flags references to puzzles and puzzle‐solving contexts (e.g. “puzzle,” “grid,” “solve,” “steps,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     puzzle
    -2.17
     puzzles
    -1.98
    puzzle
    -1.82
    Puzzle
    -1.76
     Puzzles
    -1.72
     Puzzle
    -1.69
     puja
    -1.26
    pu
    -1.23
     Puja
    -1.18
     PU
    -1.14
    POSITIVE LOGITS
     pieces
    0.99
     solved
    0.96
     solving
    0.93
     Pieces
    0.91
     Solving
    0.87
     solvable
    0.85
    プラ
    0.82
    EdgeInsets
    0.82
    月
    0.82
     solve
    0.81
    Activations Density 0.014%

    No Known Activations