© 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. 104792
    Prev
    Next
    INDEX
    Explanations

    professions, services, and entities

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

    The neuron flags numeric expressions—digits, percentages, ages, monetary amounts, measurements—wherever quantitative values appear.

    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
    Característica
    -1.37
    ÈNE
    -1.33
     arrêter
    -1.30
    Dentro
    -1.30
     cliquer
    -1.27
     zoude
    -1.26
     contenir
    -1.25
    sedown
    -1.24
    Whilst
    -1.24
     canales
    -1.22
    POSITIVE LOGITS
     based
    1.38
     because
    1.30
     analyzed
    1.19
     while
    1.16
    είτε
    1.13
     displayed
    1.12
     examining
    1.12
    んでいます
    1.09
     examined
    1.09
     More
    1.09
    Activations Density 0.275%

    No Known Activations