© 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. 84163
    Prev
    Next
    INDEX
    Explanations

    States Senate, Matrix metallo, Abish

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

    The neuron fires on the “Category:” marker in Wikipedia text (i.e. the colon token immediately following “Category”).

    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
    雜誌
    -1.09
    besondere
    -1.03
     Übersicht
    -0.98
    ólico
    -0.98
    nique
    -0.94
    tidos
    -0.94
    umumkan
    -0.94
    Elaboración
    -0.93
     akci
    -0.93
    =’
    -0.93
    POSITIVE LOGITS
    Terminator
    0.97
    radians
    0.94
    ,
    0.86
    悵
    0.85
    这里
    0.84
    esía
    0.82
    Relational
    0.82
    '
    0.82
    MT
    0.81
    жений
    0.81
    Activations Density 0.000%

    No Known Activations