© 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. 22-GEMMASCOPE-RES-131K
    7. 71281
    Prev
    Next
    INDEX
    Explanations

    finality or ending

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

    The neuron is strongly activated by numeric tokens (digits or numbers) 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_22/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
     begin
    -1.31
     start
    -1.21
    เริ่ม
    -1.14
     begins
    -1.13
     Secondly
    -1.12
     initially
    -1.11
    第一个
    -1.09
     starts
    -1.07
     first
    -1.07
    orElseThrow
    -1.06
    POSITIVE LOGITS
     final
    1.80
     finishing
    1.66
     ending
    1.62
     finish
    1.52
    finishing
    1.49
    最後は
    1.43
     finished
    1.43
     finale
    1.38
    final
    1.36
     finalize
    1.32
    Activations Density 0.014%

    No Known Activations