© 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. 13149
    Prev
    Next
    INDEX
    Explanations

    closing tags and final words

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

    The neuron primarily activates on numeric tokens—digits, numbers, and numeric literals.

    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
    strecke
    -0.95
    рі
    -0.89
    isição
    -0.87
    🥈
    -0.85
    uern
    -0.83
    hintText
    -0.82
     wilden
    -0.82
    벳
    -0.82
    atora
    -0.82
     España
    -0.81
    POSITIVE LOGITS
     final
    1.66
     cuối
    1.59
    final
    1.41
     finally
    1.24
    最終
    1.19
    最後
    1.16
     schließlich
    1.14
     lastly
    1.08
     concludes
    1.05
    Final
    1.03
    Activations Density 0.018%

    No Known Activations