© 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. 22-GEMMASCOPE-RES-131K
    7. 69173
    Prev
    Next
    INDEX
    Explanations

    numerical prices in millions

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

    This neuron detects and highlights large numeric tokens, especially monetary amounts (e.g. prices).

    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
     I
    -1.28
    T
    -1.13
    con
    -1.11
    a
    -1.11
     like
    -1.06
     muhimu
    -1.05
    N
    -1.05
    each
    -1.05
    he
    -1.05
    M
    -1.03
    POSITIVE LOGITS
    Suka
    1.46
     camiset
    1.43
     salonu
    1.38
    Rumah
    1.37
     podla
    1.31
    ⃢
    1.31
     kalori
    1.30
    ⛦
    1.30
     incrí
    1.29
    Fakta
    1.29
    Activations Density 0.013%

    No Known Activations