© 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. 12913
    Prev
    Next
    INDEX
    Explanations

    Fran, Frank, France, French

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

    This neuron fires on tokens containing the substring “Fran” (e.g. French, Franks, Fran, Frankly).

    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
    ↵
    -3.58
     
    -3.09
     a
    -2.61
    何故
    -2.61
    瑒
    -2.52
    </strong>
    -2.50
    ↵↵
    -2.42
    灃
    -2.39
    カッコいい
    -2.33
    ﻒ
    -2.30
    POSITIVE LOGITS
    providedIn
    2.39
    oooo
    2.39
     Terbaru
    2.36
    2
    2.34
    ったので
    2.33
    ”،
    2.28
    b
    2.28
    齤
    2.27
    ooo
    2.25
     پیشن
    2.25
    Activations Density 0.024%

    No Known Activations