© 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. 85252
    Prev
    Next
    INDEX
    Explanations

    Airbus, antidepressants

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

    This neuron fires strongly on prominent topic‐denoting nouns—i.e. the key subject words that signal what the section or document is mainly about.

    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
     但
    -2.55
    colgante
    -2.52
     helicóptero
    -2.23
     achten
    -2.17
     \&
    -2.17
     vanguardia
    -2.08
    ‐
    -2.08
    沨
    -2.06
     sép
    -2.06
     就
    -2.05
    POSITIVE LOGITS
    al
    2.58
    t
    2.53
    .
    2.45
    为啥
    2.41
     jakość
    2.38
    #
    2.31
     kolory
    2.23
    هایی
    2.23
    的那个
    2.20
    ll
    2.13
    Activations Density 0.004%

    No Known Activations