© 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. 9072
    Prev
    Next
    INDEX
    Explanations

    APK, Leipzig, Toulouse

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

    The neuron fires on capitalized tokens—particularly acronyms (e.g. “APK”) and proper nouns (e.g. “Leipzig,” “Toulouse”).

    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
    辄
    -2.44
     burdened
    -2.09
     or
    -2.09
     permitem
    -2.09
     capable
    -2.08
     utilizing
    -2.02
     preferably
    -1.95
    ▜
    -1.95
     начале
    -1.94
    áneas
    -1.93
    POSITIVE LOGITS
    s
    4.44
    1
    2.86
    ーズン
    2.70
    4
    2.66
    a
    2.59
    3
    2.47
    在
    2.42
    ی
    2.38
    6
    2.34
    ↵
    2.30
    Activations Density 0.001%

    No Known Activations