© 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. 102398
    Prev
    Next
    INDEX
    Explanations

    geographical locations and specific terms

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

    The neuron detects subword fragments that occur in proper names and named entities (e.g. place names, language codes, library names).

    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
     encantador
    -1.45
     from
    -1.36
     企業
    -1.30
     Meningkatkan
    -1.23
     简介
    -1.19
     rangka
    -1.17
    ｣
    -1.17
    lète
    -1.17
    』(
    -1.17
    rió
    -1.16
    POSITIVE LOGITS
    ₤
    1.53
     whom
    1.44
    ppling
    1.37
    aupun
    1.34
    ۣ
    1.33
    They
    1.33
     Также
    1.31
    zieć
    1.31
    alamu
    1.30
    だけでなく
    1.30
    Activations Density 0.006%

    No Known Activations