© 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. 124757
    Prev
    Next
    INDEX
    Explanations

    asking why

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

    This neuron detects quantifying expressions—both numeric tokens and general-purpose quantifiers (e.g. “some,” “other,” “such,” “more”).

    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
    ſten
    -1.69
     that
    -1.64
     sabía
    -1.58
     vivía
    -1.55
     něj
    -1.48
     It
    -1.48
     traducciones
    -1.44
     obtenidos
    -1.44
     sufrió
    -1.43
     necesitaba
    -1.39
    POSITIVE LOGITS
    te
    1.38
    nemia
    1.29
    would
    1.26
    せて
    1.26
    th
    1.23
    じて
    1.22
    id
    1.22
    why
    1.21
    those
    1.20
    Why
    1.19
    Activations Density 0.025%

    No Known Activations