© 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. 90716
    Prev
    Next
    INDEX
    Explanations

    silver coin coinage

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

    The neuron fires on coin‐product specification details—especially numeric year or weight values alongside terms like “Silver,” “Proof,” and “Coin.”

    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
    незон
    -0.74
    íficos
    -0.72
    measured
    -0.72
    chman
    -0.72
     confes
    -0.72
    เป๋า
    -0.71
    իվ
    -0.71
    equipped
    -0.71
     gâ
    -0.70
    Chances
    -0.70
    POSITIVE LOGITS
     coin
    2.08
     coins
    2.05
     coinage
    1.62
     Coin
    1.47
     Coins
    1.42
    coin
    1.23
     silver
    1.13
     моне
    1.11
    Coin
    1.10
     tokens
    1.08
    Activations Density 0.017%

    No Known Activations