© 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. 98301
    Prev
    Next
    INDEX
    Explanations

    final stage or conclusion

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

    This neuron detects discourse markers that signal the culmination or result of a sequence of events (e.g. culminating, eventually, result).

    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
    Immediately
    -1.52
    immediately
    -1.47
     zároveň
    -1.39
     sofort
    -1.24
     rozpoczę
    -1.23
     Immediately
    -1.20
     inmediatamente
    -1.19
     zaraz
    -1.16
     comenzar
    -1.16
     szybko
    -1.13
    POSITIVE LOGITS
     finally
    2.02
     eventually
    1.92
     schließlich
    1.73
     culminated
    1.58
     culminating
    1.56
     ultimately
    1.53
     Eventually
    1.48
     infine
    1.48
     when
    1.43
    最终
    1.40
    Activations Density 0.047%

    No Known Activations