© 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. 48075
    Prev
    Next
    INDEX
    Explanations

    Russian prefixes; foreign prefixes; plus/minus

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

    This neuron consistently fires on capitalized Latin prefixes like “Pro” or “Ré” at the start of 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_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
    ↵↵
    -2.75
    s
    -2.56
     když
    -2.50
    }
    -2.47
     
    -2.45
     '
    -2.28
    </td>
    -2.25
     bekannten
    -2.23
     interrump
    -2.22
     aconse
    -2.16
    POSITIVE LOGITS
    >
    3.06
     classico
    2.86
     disel
    2.81
     手绘
    2.81
     sabar
    2.69
     boken
    2.67
    媜
    2.66
     umbro
    2.59
     aperta
    2.55
     officiels
    2.53
    Activations Density 0.001%

    No Known Activations