© 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. 92880
    Prev
    Next
    INDEX
    Explanations

    bibliography / external links

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

    The neuron fires strongly on bibliography and in‐text citation markers (e.g. reference tags like “[B1]” or author–year citations).

    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
     which
    -1.59
     from
    -1.30
     at
    -1.30
    ##############
    -1.23
     pistola
    -1.10
     ४
    -1.09
     pemeriksaan
    -1.08
     pengobatan
    -1.05
     pemberian
    -1.05
     pelayanan
    -1.05
    POSITIVE LOGITS
    larıyla
    1.20
     largely
    1.10
    increasing
    1.09
    potentially
    1.08
    increased
    1.06
     tóxic
    1.05
     ersche
    1.05
    でない
    1.05
     dianteiro
    1.04
     ワン
    1.04
    Activations Density 0.035%

    No Known Activations