© 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. 34-GEMMASCOPE-RES-131K
    7. 116825
    Prev
    Next
    INDEX
    Explanations

    self method calls

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

    The neuron activates on numeric literals (sequences of digits) 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_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
     its
    -0.86
     siguientes
    -0.83
    игра
    -0.82
     Therefore
    -0.79
    Qaeda
    -0.77
    窒
    -0.77
     своей
    -0.75
    camb
    -0.74
    Fermi
    -0.74
     moest
    -0.72
    POSITIVE LOGITS
     Nicolai
    1.01
     日記
    0.91
     jestli
    0.88
    HStack
    0.86
    ędziesz
    0.85
     accordo
    0.84
    verticalLayout
    0.84
     Dogecoin
    0.83
     Maulana
    0.82
     mentioned
    0.82
    Activations Density 0.001%

    No Known Activations