© 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. 22-GEMMASCOPE-RES-131K
    7. 68269
    Prev
    Next
    INDEX
    Explanations

    numbers and technical terms

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

    The neuron strongly activates on standalone numeric digits.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Kenapa
    -1.28
     to
    -1.16
     mostly
    -1.05
    之助
    -1.02
     sqlSession
    -0.99
     STATE
    -0.97
    における
    -0.96
     участия
    -0.96
     jeg
    -0.95
     enoj
    -0.95
    POSITIVE LOGITS
     iluminación
    1.16
     natuurlijke
    1.14
     soldadura
    1.13
     soportes
    1.12
     ventilación
    1.12
     bijzondere
    1.11
     suelos
    1.11
     oznacza
    1.09
     verbinding
    1.09
     ontwerp
    1.08
    Activations Density 0.003%

    No Known Activations