© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60671
    Prev
    Next
    INDEX
    Explanations

    board game files

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

    The neuron responds to numeric tokens, activating on numbers and numeric values in the text.

    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
    fono
    -0.88
     watchman
    -0.81
    istus
    -0.80
    khidmatan
    -0.78
     shrew
    -0.77
     carnal
    -0.74
     immunotherapy
    -0.73
    国产
    -0.72
    トンネル
    -0.71
     timbre
    -0.71
    POSITIVE LOGITS
     file
    1.37
     files
    1.27
     rank
    1.25
     Files
    1.24
    Board
    1.23
    Rank
    1.22
    Files
    1.22
    BOARD
    1.19
     ranks
    1.18
     FILE
    1.14
    Activations Density 0.004%

    No Known Activations