© 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. 34-GEMMASCOPE-RES-131K
    4. 38385
    Prev
    Next
    INDEX
    Explanations

    soil or citation markers

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

    academic citation patterns in scholarly articles.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on in-text citation markers (e.g. the “[ @… ]” bibliography key tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    oneofs
    -0.73
    více
    -0.73
    เชื่อ
    -0.70
     здание
    -0.70
    stered
    -0.69
     pisos
    -0.68
    direkt
    -0.68
     memu
    -0.68
    /////////////
    -0.68
    crystal
    -0.68
    POSITIVE LOGITS
     soil
    1.66
    Soil
    1.53
     Soil
    1.52
     soils
    1.28
    soil
    1.17
     SOIL
    1.15
    SOIL
    1.13
    土壤
    1.11
     Soils
    1.06
     suelos
    0.94
    Activations Density 0.005%

    No Known Activations