© 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. 34-GEMMASCOPE-RES-131K
    4. 91186
    Prev
    Next
    INDEX
    Explanations

    android, obtaining

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

    The neuron fires on numeric literals (sequences of digits) wherever they appear in the code or 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_34/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
    either
    -1.02
    Either
    -0.90
     itself
    -0.88
     either
    -0.88
     himself
    -0.87
    itieren
    -0.86
    Два
    -0.86
    تهم
    -0.84
     both
    -0.82
    انواع
    -0.82
    POSITIVE LOGITS
    ဩ
    0.89
    nss
    0.87
     parfaite
    0.85
    йтесь
    0.84
    の問題
    0.82
     dasselbe
    0.81
     Bayesian
    0.79
    !(:
    0.78
     elseif
    0.78
     ogranic
    0.78
    Activations Density 0.006%

    No Known Activations