© 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. 34-GEMMASCOPE-RES-131K
    4. 73488
    Prev
    Next
    INDEX
    Explanations

    in a specific context

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

    The neuron picks out technical terms denoting scientific measurements or experimental analyses (e.g. “examinations,” “perfusion,” “analysis,” “parameters”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    cannot
    -1.29
     görd
    -1.21
    anglais
    -1.20
    whenever
    -1.14
     discuter
    -1.13
    produksi
    -1.12
    Cannot
    -1.10
    puede
    -1.10
     refroid
    -1.09
     Cannot
    -1.09
    POSITIVE LOGITS
     longtime
    1.16
     determined
    1.16
     researched
    1.16
     with
    1.14
     in
    1.09
     depending
    1.05
     belonging
    1.05
     without
    1.05
     for
    1.02
     at
    1.01
    Activations Density 0.062%

    No Known Activations