© 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. 90334
    Prev
    Next
    INDEX
    Explanations

    research, corporation, and points

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

    The neuron detects mentions of quantitative preference–elicitation methods and evaluation tools (e.g. surveys, polls, discrete choice or conjoint analyses).

    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
     had
    -1.38
     just
    -1.34
     unusually
    -1.23
     so
    -1.18
     that
    -1.17
     because
    -1.17
     can
    -1.16
     this
    -1.15
     about
    -1.15
     for
    -1.14
    POSITIVE LOGITS
    🐐
    1.35
    ">“
    1.32
    ће
    1.27
    ಠ
    1.24
    ceptibility
    1.18
    からない
    1.17
    charpe
    1.16
    lers
    1.16
     acessar
    1.13
     bedien
    1.13
    Activations Density 0.095%

    No Known Activations