© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74924
    Prev
    Next
    INDEX
    Explanations

    loan and deposit requirements

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

    The neuron is tuned to spot banking/finance jargon – in particular names of account‐ and payment-related products or institutions (e.g. deposit, account, FDIC, ACH, CD, money-market).

    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
    b
    -1.41
     redan
    -1.35
     -
    -1.35
    mp
    -1.30
    Ꭱ
    -1.29
    ”-
    -1.27
     Already
    -1.26
    Aries
    -1.26
    os
    -1.25
    g
    -1.25
    POSITIVE LOGITS
     you
    1.66
     instead
    1.63
     like
    1.51
    涐
    1.41
     they
    1.38
     or
    1.36
     rather
    1.35
    佧
    1.27
     and
    1.27
     to
    1.27
    Activations Density 0.119%

    No Known Activations