© 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. 69255
    Prev
    Next
    INDEX
    Explanations

    citations ending in ]

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

    The neuron detects in‐text scholarly citation markers (e.g. bracketed reference codes and 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
     to
    -1.88
     from
    -1.41
     without
    -1.38
     by
    -1.35
     if
    -1.30
     as
    -1.29
     what
    -1.27
     where
    -1.19
     with
    -1.17
     at
    -1.16
    POSITIVE LOGITS
     frequentemente
    1.20
     dette
    1.15
     écouter
    1.09
     inserir
    1.09
     archetype
    1.08
     například
    1.07
     intégr
    1.06
    msgstr
    1.04
    がたくさん
    1.03
    alış
    1.02
    Activations Density 0.132%

    No Known Activations