© 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. 28179
    Prev
    Next
    INDEX
    Explanations

    designates a, an, the, lamp, line

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

    The neuron activates on numeric tokens, especially reference numerals, measurements, and other numbers in technical text.

    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
    Nós
    -1.59
    Então
    -1.42
    Muito
    -1.38
    Minha
    -1.37
    Ótimo
    -1.32
    Assista
    -1.30
    Quais
    -1.26
    Informações
    -1.25
    Obrigado
    -1.25
    Possui
    -1.24
    POSITIVE LOGITS
     нарушение
    1.10
     with
    1.09
     регули
    1.04
     Jehová
    1.02
     receives
    1.02
     forming
    1.01
     warmer
    1.00
    养成
    1.00
     нарушения
    0.99
     always
    0.98
    Activations Density 0.003%

    No Known Activations