© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47557
    Prev
    Next
    INDEX
    Explanations

    Place Prize or Delivery Available

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

    The neuron detects standalone numeric tokens (quantities, statistics, dates, prices, etc.) 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
     lorsque
    -1.53
    を終
    -1.27
    licitations
    -1.25
     quando
    -1.23
     Gelegenheit
    -1.20
    umers
    -1.19
    tuce
    -1.18
     когато
    -1.18
    cji
    -1.17
     projektu
    -1.17
    POSITIVE LOGITS
     that
    1.37
     to
    1.34
     ”
    1.25
     する
    1.21
     pediu
    1.20
    (""+
    1.20
     all
    1.16
     ''
    1.16
     būtų
    1.13
     such
    1.13
    Activations Density 0.008%

    No Known Activations