© 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. 10-GEMMASCOPE-RES-131K
    4. 71125
    Prev
    Next
    INDEX
    Explanations

    citations and references

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

    This neuron detects numeric reference or citation identifiers (e.g. numbers in square-bracket citations or bibliography keys).

    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
     to
    -1.73
    cnbc
    -1.55
     the
    -1.45
     into
    -1.39
    .''
    -1.38
     at
    -1.37
     then
    -1.30
     creatividad
    -1.30
    libat
    -1.28
     Entsche
    -1.24
    POSITIVE LOGITS
    zation
    1.57
    ↵↵
    1.48
     åren
    1.42
    5
    1.34
     hjär
    1.34
    unordered
    1.32
     edile
    1.31
    难以
    1.30
     vores
    1.30
     begge
    1.26
    Activations Density 0.052%

    No Known Activations