© 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. 38183
    Prev
    Next
    INDEX
    Explanations

    binary numbers and sequences

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

    The neuron strongly activates on tokens that are numeric literals (sequences of digits, including digits in different bases).

    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
     by
    -1.08
     same
    -1.05
     five
    -1.01
     eight
    -0.99
     also
    -0.99
     asked
    -0.95
     their
    -0.93
     six
    -0.93
     exactly
    -0.92
     nine
    -0.92
    POSITIVE LOGITS
     poë
    0.93
     Viro
    0.93
     temb
    0.91
     Pary
    0.90
     vissa
    0.90
     serre
    0.89
     Ă
    0.88
     одним
    0.88
    iap
    0.87
    ζί
    0.85
    Activations Density 0.013%

    No Known Activations