© 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. 10-GEMMASCOPE-RES-131K
    7. 69330
    Prev
    Next
    INDEX
    Explanations

    OutOfRange Exception

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

    The neuron activates on proper‐name tokens—i.e. capitalized identifiers such as personal names, project or library names, species names, and other named entities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    because
    -3.42
    ஂ
    -2.66
    which
    -2.64
    i
    -2.53
    
    -2.36
    哪个
    -2.36
     οποία
    -2.31
     reconocida
    -2.30
    !!!!!
    -2.30
    ......
    -2.30
    POSITIVE LOGITS
    翃
    3.70
    姈
    3.22
    I
    2.73
    鶫
    2.70
     Ensuring
    2.63
     Internation
    2.50
     Effectively
    2.48
    壜
    2.47
    玙
    2.45
     entièrement
    2.44
    Activations Density 0.047%

    No Known Activations