© 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. 22-GEMMASCOPE-RES-131K
    4. 332
    Prev
    Next
    INDEX
    Explanations

    numbers and descriptive words

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

    The neuron specializes in spotting numerical information—quantities, measurements, and other numeric expressions—in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    comparative and superlative constructions, particularly phrases describing size, scale, or ranking relationships.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    Сейчас
    -1.45
    ociação
    -1.36
    itoriale
    -1.29
    titian
    -1.23
     古着
    -1.20
     другим
    -1.19
    Istorija
    -1.19
     årets
    -1.18
     يبدو
    -1.16
     balení
    -1.15
    POSITIVE LOGITS
     three
    1.77
     five
    1.70
     two
    1.70
     their
    1.49
     so
    1.41
     in
    1.38
     four
    1.38
     six
    1.37
     every
    1.35
     seven
    1.34
    Activations Density 0.036%

    No Known Activations