© 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. 22-GEMMASCOPE-RES-131K
    4. 74984
    Prev
    Next
    INDEX
    Explanations

    Tx, outputs, transactions, Module

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

    The neuron strongly activates on technical blockchain jargon—especially terms related to transactions (e.g. “transaction,” “outputs,” “standard transaction,” “policy,” “weight,” “transactions”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    dä
    -1.40
    ׄ
    -1.36
     शुर
    -1.30
     where
    -1.25
    thiet
    -1.21
    FUENTES
    -1.20
    ∽
    -1.20
     and
    -1.20
    📇
    -1.18
    ❤️❤️❤️
    -1.17
    POSITIVE LOGITS
     ダイ
    1.23
     деталей
    1.23
    FontAwesomeIcon
    1.21
    🧫
    1.20
     Oblast
    1.17
    AFFIRMED
    1.15
    RIES
    1.13
     чехол
    1.13
     токси
    1.12
    风险
    1.11
    Activations Density 0.007%

    No Known Activations