© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84288
    Prev
    Next
    INDEX
    Explanations

    academic papers analyze and propose

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

    The neuron detects discourse markers introducing or referring to the paper itself—phrases like “This article…,” “In particular…,” “Based on…,” and “The article proposes…” that outline the study’s aims or structure.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the beginning of academic article text, particularly after the title and abstract, where the main argument or discussion starts.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     even
    -1.53
     when
    -1.43
    formatics
    -1.41
    ^
    -1.38
     tampaknya
    -1.38
    ♪♪
    -1.30
    维基
    -1.30
    DetailComponent
    -1.26
    ↑↑↑
    -1.24
    ництва
    -1.23
    POSITIVE LOGITS
     drei
    1.41
     enquanto
    1.39
     três
    1.38
     Bemerkungen
    1.30
    yorsunuz
    1.29
    它
    1.27
     бампер
    1.25
    把我
    1.23
     freio
    1.21
     fünf
    1.20
    Activations Density 0.149%

    No Known Activations