© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130973
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on semantically rich content words—key nouns, verbs, and adjectives that carry the main topical information of a passage—while ignoring common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    academic or professional titles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ⁡
    -1.02
     Libertadores
    -1.01
    ámicas
    -1.00
     rakyat
    -0.99
     sodass
    -0.98
     Ríos
    -0.97
     CORPORATION
    -0.96
     \
    
    -0.96
    giver
    -0.94
     selatan
    -0.94
    POSITIVE LOGITS
    Also
    1.12
     other
    1.01
     also
    0.98
    另一个
    0.96
     மற்ற
    0.94
    他の
    0.93
    lipas
    0.92
    龵
    0.91
     adicional
    0.90
    另外
    0.88
    Activations Density 0.038%

    No Known Activations