© 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. 20966
    Prev
    Next
    INDEX
    Explanations

    financial amounts

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

    The neuron is tuned to detect numeric literals that represent amounts (e.g. “amount”, “SUM(amount)”, monetary values) in code or prose.

    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
     berikan
    -1.96
    ”:
    -1.96
    ”-
    -1.88
    }$
    -1.85
    ;
    -1.80
     dapatkan
    -1.78
    #%%
    -1.77
    in
    -1.77
    !!!”
    -1.76
    LA
    -1.65
    POSITIVE LOGITS
    很赞
    1.95
    じゃあ
    1.81
    很喜欢
    1.73
    余談
    1.66
     apont
    1.64
     škola
    1.62
     \
    1.61
    後日
    1.55
     jovens
    1.55
     amount
    1.55
    Activations Density 0.020%

    No Known Activations