© 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. 22-GEMMASCOPE-RES-131K
    4. 84284
    Prev
    Next
    INDEX
    Explanations

    code structures and keywords

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

    This neuron detects numeric tokens (numbers and numeric literals) 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_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
    Considering
    -1.12
    Then
    -1.09
    昨日は
    -1.09
     способствует
    -1.05
    %;
    -1.05
    おはよう
    -1.02
    今年も
    -1.02
    にほんブログ村
    -1.02
    朝廷
    -1.00
    __',
    -1.00
    POSITIVE LOGITS
    jari
    1.09
    などは
    0.99
    яд
    0.98
    city
    0.96
    NOWLEDG
    0.96
     Perusahaan
    0.95
    uestions
    0.90
    СЕ
    0.90
    СТО
    0.90
    СКА
    0.90
    Activations Density 0.007%

    No Known Activations