© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117726
    Prev
    Next
    INDEX
    Explanations

    periods, specified, public

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

    The neuron fires on multi‐digit numeric tokens (i.e. sequences of digits).

    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
    OTO
    -0.83
     hiệu
    -0.77
    avannah
    -0.77
     Orthop
    -0.75
    Symmetry
    -0.75
     סי
    -0.71
     kepada
    -0.71
    IMAS
    -0.70
     Kum
    -0.68
     Byrne
    -0.68
    POSITIVE LOGITS
    nsis
    0.70
    下車
    0.69
    TT
    0.68
     unfortunate
    0.66
     learning
    0.65
    ଲ
    0.64
    仙台
    0.63
    喎
    0.63
     rifer
    0.63
    こんなに
    0.62
    Activations Density 0.039%

    No Known Activations