© 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. 97961
    Prev
    Next
    INDEX
    Explanations

    final stages, third place, Oscar

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

    The neuron is strongly activated by numeric tokens and digit sequences (e.g. dates, years, and other numbers).

    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
     vivir
    -0.90
    Lycka
    -0.88
     žena
    -0.85
     biking
    -0.84
     cogni
    -0.83
     laser
    -0.81
    navBar
    -0.81
     online
    -0.81
     conciertos
    -0.81
    ůj
    -0.80
    POSITIVE LOGITS
     Ecu
    1.09
     thereafter
    0.99
    readystatechange
    0.98
     postwar
    0.97
     entrant
    0.92
    chassis
    0.91
     jugos
    0.88
     Yugoslav
    0.85
    场地
    0.84
     Lightweight
    0.84
    Activations Density 0.033%

    No Known Activations