© 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. 75078
    Prev
    Next
    INDEX
    Explanations

    probability, hypothesis, rule, advantages

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

    The neuron responds to technical research and measurement terms—especially methodological/statistical phrases (e.g. “growth rate,” “probability,” “hypothesis,” “in vivo/in vitro,” “stimulus–response”).

    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
     ativar
    -1.36
     escolher
    -1.28
     acrescent
    -1.24
    给人
    -1.23
    Including
    -1.23
     recém
    -1.23
    铪
    -1.21
     terão
    -1.21
     voltar
    -1.20
     baixar
    -1.20
    POSITIVE LOGITS
     for
    1.96
     his
    1.56
     by
    1.55
     even
    1.48
     both
    1.44
     many
    1.43
     our
    1.41
     on
    1.36
     maupun
    1.28
     in
    1.27
    Activations Density 0.744%

    No Known Activations