© 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. 79537
    Prev
    Next
    INDEX
    Explanations

    field names and types

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

    The neuron fires on in-word uppercase letters—i.e. the capital letters used in CamelCase or PascalCase identifiers.

    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
     vokal
    -1.20
     Meksi
    -1.20
    مقاله
    -1.16
     kalori
    -1.16
     kalem
    -1.16
     lyder
    -1.16
     kutu
    -1.14
    Filmo
    -1.14
     radikal
    -1.12
    alucía
    -1.11
    POSITIVE LOGITS
     ursprünglich
    1.35
     ursprünglichen
    1.27
     worin
    1.27
     offiziell
    1.17
    roffene
    1.13
     мужская
    1.13
     gewöhnlich
    1.12
     späteren
    1.12
     Other
    1.11
    といいます
    1.09
    Activations Density 0.002%

    No Known Activations