© 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. 67523
    Prev
    Next
    INDEX
    Explanations

    automated teller machine

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

    The neuron detects occurrences of the acronym “ATM” (and its expanded forms such as Automated Teller Machine or Asynchronous Transfer Mode).

    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
     الأخرى
    -2.50
     نفسها
    -2.42
     soared
    -2.41
    呖
    -2.38
    اً
    -2.38
    、“
    -2.31
    which
    -2.27
    鄚
    -2.25
     necessárias
    -2.25
     Now
    -2.19
    POSITIVE LOGITS
    '
    2.73
    閦
    2.69
     sowohl
    2.52
     you
    2.31
     There
    2.20
    ization
    2.13
     conjunction
    2.09
     становится
    2.02
     abhängig
    2.02
     What
    1.99
    Activations Density 0.006%

    No Known Activations