© 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. 100207
    Prev
    Next
    INDEX
    Explanations

    currency symbols and amounts

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

    The neuron fires on dollar‐sign price figures (i.e. monetary amounts expressed with a “$” followed by numbers).

    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
    and
    -2.31
     is
    -1.94
     и
    -1.93
    Ｒ
    -1.91
    c
    -1.90
    ）
    -1.90
    でも
    -1.87
     και
    -1.86
    ২
    -1.86
     as
    -1.84
    POSITIVE LOGITS
    ＝＝＝＝
    2.11
    ࿚
    1.90
    Stap
    1.86
    俺は
    1.84
     показать
    1.83
    わけで
    1.78
    了一個
    1.77
    瞜
    1.77
     incred
    1.76
    わけではない
    1.76
    Activations Density 0.002%

    No Known Activations