© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130382
    Prev
    Next
    INDEX
    Explanations

    fundraising, finances, budgets

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

    The neuron fires on terms and numbers related to government or organizational budgetary and revenue figures.

    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
     komplet
    -1.81
     kontaktu
    -1.66
    の商品
    -1.63
    filé
    -1.55
     observación
    -1.51
     заинтере
    -1.51
    が終わ
    -1.50
     stessa
    -1.50
     confirmación
    -1.49
    튿
    -1.49
    POSITIVE LOGITS
     we
    1.75
     of
    1.63
     essential
    1.44
     without
    1.44
     has
    1.40
    There
    1.38
     Without
    1.37
     dasarnya
    1.35
     our
    1.33
     which
    1.30
    Activations Density 0.009%

    No Known Activations