© 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. 10-GEMMASCOPE-RES-131K
    7. 21739
    Prev
    Next
    INDEX
    Explanations

    omega-3 fatty acids

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

    dimensional measurements involving "x" notation (like 2x4, 3x6, Omega-3).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric dimension expressions (e.g. “2 x 4”, “3′ × 6”) indicating measurements or sizes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ”
    -1.90
    ”;
    -1.60
    owulf
    -1.58
    )”
    -1.54
    ”),
    -1.52
     Hivatalos
    -1.51
    】:
    -1.47
    ’
    -1.46
    ）
    -1.45
    ”)
    -1.44
    POSITIVE LOGITS
    ̜
    1.42
     myśli
    1.39
    レン
    1.38
     relentlessly
    1.36
     fortfarande
    1.35
    ización
    1.34
     planète
    1.33
     españa
    1.32
    烘焙
    1.32
    嚆
    1.31
    Activations Density 0.025%

    No Known Activations