© 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. 27951
    Prev
    Next
    INDEX
    Explanations

    legal citations and academic papers

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

    The neuron fires on multi‐digit sequences—especially four‐digit year or citation numbers.

    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
    そして
    -1.11
    は
    -1.06
     have
    -1.05
    defining
    -1.05
     benzin
    -0.99
     komment
    -0.95
    并且
    -0.92
    餃
    -0.92
    だが
    -0.92
    ٢
    -0.91
    POSITIVE LOGITS
    向けの
    1.00
    pozycji
    1.00
     unangemessene
    0.98
     sıcak
    0.93
    etches
    0.93
    aporation
    0.91
    ℹ
    0.91
     erwäh
    0.91
    ってる
    0.90
    metheus
    0.90
    Activations Density 0.001%

    No Known Activations