© 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. 71744
    Prev
    Next
    INDEX
    Explanations

    price and value

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

    The neuron fires on numerical tokens—especially decimal financial figures—i.e., it detects numbers and numeric values in the text.

    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
    甗
    -1.84
    镲
    -1.73
    />
    -1.71
     Rptr
    -1.62
    辚
    -1.59
    鼍
    -1.58
    缡
    -1.57
    𓆏
    -1.56
    卣
    -1.56
    ()
    -1.56
    POSITIVE LOGITS
     if
    1.88
    '
    1.87
     when
    1.86
     after
    1.57
    This
    1.49
     this
    1.47
    when
    1.46
     This
    1.45
     perhaps
    1.45
     biggest
    1.44
    Activations Density 0.009%

    No Known Activations