© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19347
    Prev
    Next
    INDEX
    Explanations

    performance, quality, condition

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

    The neuron fires on numeric quantity expressions—especially multi‐digit numbers and decimal values used in technical or measurement contexts.

    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
     and
    -1.45
     which
    -1.34
    </i>
    -1.29
     at
    -1.27
    ∶
    -1.24
     since
    -1.23
     different
    -1.22
    ệc
    -1.22
     every
    -1.22
     all
    -1.22
    POSITIVE LOGITS
    々は
    1.23
     getNome
    1.21
     dénon
    1.18
     Apakah
    1.13
     красивый
    1.12
     Bedürf
    1.10
     Akhir
    1.09
    formato
    1.07
     качества
    1.05
    ENTRE
    1.04
    Activations Density 0.112%

    No Known Activations