© 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. 84637
    Prev
    Next
    INDEX
    Explanations

    dollar amounts

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

    The neuron detects numeric tokens that are part of monetary amounts (numbers following a currency sign like “$”).

    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
    ;
    -1.74
     October
    -1.43
     one
    -1.37
     and
    -1.34
     September
    -1.31
    ,
    -1.30
     November
    -1.30
     July
    -1.28
     two
    -1.25
     during
    -1.25
    POSITIVE LOGITS
     they
    1.88
     ciencias
    1.73
    訁
    1.55
     eixo
    1.45
    ."
    1.42
    ('
    1.42
     vín
    1.42
    ？”
    1.41
    癀
    1.41
     ними
    1.38
    Activations Density 0.010%

    No Known Activations