© 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. 54463
    Prev
    Next
    INDEX
    Explanations

    citations and publication details

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

    The neuron is triggered by the punctuation and connector tokens used to separate and mark entries in academic citations (e.g. semicolons, parentheses, “and,” “by”) within reference lists.

    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
    sprzed
    -1.62
    więks
    -1.53
    dasarkan
    -1.46
    lepiej
    -1.45
    providedIn
    -1.41
    の時間
    -1.39
     cucina
    -1.38
     Accesorios
    -1.38
     vesel
    -1.38
     that
    -1.33
    POSITIVE LOGITS
     a
    1.40
    ,
    1.33
     A
    1.30
    5
    1.26
    などは
    1.20
    2
    1.20
    1
    1.18
    4
    1.17
     M
    1.13
     C
    1.12
    Activations Density 0.000%

    No Known Activations