© 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. 10-GEMMASCOPE-RES-131K
    7. 90837
    Prev
    Next
    INDEX
    Explanations

    upon an event

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

    This neuron fires on occurrences of the Russian preposition “при.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -2.95
    is
    -2.92
    蠖
    -2.27
    izing
    -2.19
    how
    -2.14
    龵
    -2.13
    шив
    -2.13
     allgemein
    -2.11
    )
    -2.09
    栊
    -2.06
    POSITIVE LOGITS
     повітря
    2.95
    providedIn
    2.53
     點
    2.48
     推薦
    2.44
     說
    2.42
     What
    2.41
     Bedarf
    2.39
     總
    2.39
    駭
    2.36
     帳
    2.33
    Activations Density 0.001%

    No Known Activations