© 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. 33600
    Prev
    Next
    INDEX
    Explanations

    ways to do something

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

    This neuron detects Russian discourse markers and filler words (e.g. “так,” “вот,” “же,” “такая”).

    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
     така
    -1.13
     такого
    -1.00
     such
    -1.00
    趼
    -0.97
    abilità
    -0.96
     gangguan
    -0.96
     dokumen
    -0.94
     bencana
    -0.94
    如此
    -0.93
    Busch
    -0.93
    POSITIVE LOGITS
     же
    1.70
     as
    1.37
     or
    1.20
     или
    1.16
    ти
    1.14
     ώ
    1.12
    тику
    1.11
     facendo
    1.11
     that
    1.10
    Also
    1.05
    Activations Density 0.005%

    No Known Activations