© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66881
    Prev
    Next
    INDEX
    Explanations

    cryptocurrencies and blockchain

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

    The neuron activates on mentions of specific cryptocurrencies or blockchain tokens (e.g. Bitcoin, Ether, Ethereum).

    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
    ();
    -1.93
     other
    -1.78
     laiton
    -1.59
     alamat
    -1.58
     them
    -1.54
     canzone
    -1.53
     lulus
    -1.52
    蹓
    -1.52
     ditem
    -1.52
    ಗಳ
    -1.48
    POSITIVE LOGITS
    がありますが
    1.72
    咂
    1.45
    想了想
    1.36
    tividade
    1.32
     并
    1.29
    多彩
    1.27
    があります
    1.27
    CK
    1.24
    ädie
    1.24
    だけ
    1.23
    Activations Density 0.008%

    No Known Activations