© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 69973
    Prev
    Next
    INDEX
    Explanations

    concluding part

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

    This neuron responds to non-standard “tokens” made up largely of digits or punctuation (e.g. numbers in dates or ASCII-art lines) rather than ordinary words.

    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
     opener
    -1.31
     opening
    -1.17
    Opening
    -1.06
     Opening
    -1.03
    第一章
    -0.95
    GenerationType
    -0.93
     बीच
    -0.90
     intermediate
    -0.89
    OnInit
    -0.89
     midterm
    -0.89
    POSITIVE LOGITS
     final
    1.73
     finale
    1.70
     concluding
    1.50
    Final
    1.48
     Finale
    1.42
     Final
    1.38
    final
    1.38
    Finale
    1.34
     FINAL
    1.30
     closing
    1.27
    Activations Density 0.085%

    No Known Activations