© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73560
    Prev
    Next
    INDEX
    Explanations

    citation markers like [@R]

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

    The neuron detects reference citation numbers (the numbered tags in brackets or superscripts).

    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
     of
    -1.23
    جموع
    -1.02
    it
    -0.98
    jść
    -0.96
    ับ
    -0.82
     vẫn
    -0.80
     in
    -0.79
     уточ
    -0.79
    hostname
    -0.79
     plezier
    -0.75
    POSITIVE LOGITS
    Tienen
    1.11
    värr
    1.04
     čier
    1.01
    や
    1.00
     originalmente
    0.99
    zaak
    0.98
     ἀ
    0.98
     Grèce
    0.98
    roduction
    0.97
     quando
    0.96
    Activations Density 0.009%

    No Known Activations