© 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. 67263
    Prev
    Next
    INDEX
    Explanations

    same source, server, account

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

    The neuron fires on words and phrases that signal sameness or shared origin (e.g. “same,” “source,” “lineage,” “as”).

    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
     its
    -1.38
     his
    -1.05
     it
    -1.05
    鸰
    -1.01
     itself
    -1.01
    它的
    -1.00
     useless
    -0.99
    ほう
    -0.98
     pertinent
    -0.98
     exceedingly
    -0.98
    POSITIVE LOGITS
    They
    1.37
     they
    1.23
     terrasse
    1.11
     mereka
    1.10
    同一个
    1.09
     हालांकि
    1.08
     same
    1.07
     Rè
    1.05
     они
    1.03
    Mereka
    1.03
    Activations Density 0.080%

    No Known Activations