© 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. 34-GEMMASCOPE-RES-131K
    7. 89928
    Prev
    Next
    INDEX
    Explanations

    Long combined with other words

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

    This neuron detects occurrences of the word “Long,” especially when it appears as part of a proper name (e.g., Long Beach, Long Island, Longridge).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     sogen
    -0.97
     brief
    -0.91
     briefly
    -0.88
    italian
    -0.85
    Gruppo
    -0.83
    Favorites
    -0.83
     générales
    -0.82
     коротки
    -0.82
     みた
    -0.81
    capri
    -0.80
    POSITIVE LOGITS
     ago
    1.73
    itudinal
    1.57
    lasting
    1.54
     lasting
    1.44
    term
    1.33
    titud
    1.30
     overdue
    1.30
     awaited
    1.23
    Term
    1.23
    titude
    1.19
    Activations Density 0.085%

    No Known Activations