© 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. 107583
    Prev
    Next
    INDEX
    Explanations

    finite number of consecutive powers

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

    The neuron fires on formal statements asserting that only finitely many of some mathematical objects exist.

    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
    ije
    -0.84
    NOST
    -0.77
    vij
    -0.74
     pears
    -0.70
    ерт
    -0.69
     VILL
    -0.69
    κε
    -0.68
     δικ
    -0.68
    Vil
    -0.68
     теку
    -0.68
    POSITIVE LOGITS
     finite
    4.97
    finite
    4.06
    Finite
    3.75
     Finite
    3.52
    有限
    3.23
     finitely
    2.86
     finito
    2.23
     有限
    2.14
     fin
    2.06
     finit
    2.03
    Activations Density 0.102%

    No Known Activations