© 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. 73788
    Prev
    Next
    INDEX
    Explanations

    listing items or sequences

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

    This neuron flags code tokens that include an underscore (i.e. parts of snake_case identifiers).

    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
     first
    -1.20
    ڼ
    -1.07
     kone
    -1.00
    但她
    -1.00
    isContained
    -0.98
    Descriere
    -0.97
     første
    -0.96
     Serikat
    -0.95
    teclado
    -0.94
    евна
    -0.93
    POSITIVE LOGITS
     their
    1.12
    either
    1.08
     respective
    0.95
    (
    
    0.91
     соответству
    0.89
     beantragt
    0.88
    amentul
    0.88
     similar
    0.88
     аналоги
    0.86
    similar
    0.86
    Activations Density 0.004%

    No Known Activations