© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78081
    Prev
    Next
    INDEX
    Explanations

    citation markers

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

    The neuron activates on numeric tokens and citation/reference markers (e.g. reference numbers, section numbers, identifiers).

    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
     usually
    -0.90
     and
    -0.90
     so
    -0.89
     almost
    -0.88
     after
    -0.86
     because
    -0.86
     nearly
    -0.84
    omis
    -0.83
    _{[
    -0.82
    といいます
    -0.81
    POSITIVE LOGITS
     Antes
    1.11
    been
    0.94
    
    0.94
    Твор
    0.92
     lejos
    0.89
     трени
    0.89
    ^_^
    0.89
     ESPEC
    0.88
     différentes
    0.88
     splendid
    0.86
    Activations Density 0.041%

    No Known Activations