© 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. 59017
    Prev
    Next
    INDEX
    Explanations

    amounts in millions and crores

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

    The neuron detects tokens that name large monetary amounts (e.g. “million,” “crore,” “m” after a numeral).

    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
     गए
    -1.59
    儡
    -1.52
     fieltro
    -1.50
     aguja
    -1.39
     chied
    -1.39
    oblo
    -1.38
    ACIONAL
    -1.38
    opathic
    -1.37
     destinées
    -1.35
    綽
    -1.35
    POSITIVE LOGITS
    ↵
    1.97
    ")
    1.75
     of
    1.71
    :\\
    1.63
    ↵↵↵↵↵↵↵↵↵↵↵
    1.63
    ↵↵↵↵↵↵↵
    1.63
    푣
    1.63
    </h3>
    1.60
     EACH
    1.58
    -\\
    1.54
    Activations Density 0.034%

    No Known Activations