© 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. 71280
    Prev
    Next
    INDEX
    Explanations

    start of entity names

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

    The neuron fires on tokens that denote financial data points—particularly numeric values, yield figures, and currency or market‐instrument abbreviations.

    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
     great
    -1.36
     much
    -1.36
     many
    -1.35
     such
    -1.31
     this
    -1.29
     very
    -1.22
     so
    -1.13
     these
    -1.10
     doing
    -1.09
     during
    -1.08
    POSITIVE LOGITS
    🪚
    1.47
    🪛
    1.34
     vermelho
    1.32
    ╒
    1.20
     amarelo
    1.19
     caminha
    1.19
     đang
    1.16
    🩹
    1.14
    Fernsehserie
    1.13
    ⾯
    1.12
    Activations Density 0.000%

    No Known Activations