© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57279
    Prev
    Next
    INDEX
    Explanations

    aspects of life and society

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

    The neuron strongly activates on nouns naming broad dimensions or components (e.g. “aspects,” “elements,” “facets,” “phases,” “quality of life,” “modern living,” “functional,” “morphological,” etc.).

    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
    丝毫
    -1.16
     ambitions
    -1.07
     девочек
    -1.05
     puissante
    -1.03
    paravant
    -1.02
    pecies
    -1.02
     urč
    -0.97
    atized
    -0.96
     typos
    -0.96
    ishments
    -0.96
    POSITIVE LOGITS
     our
    1.61
     what
    1.46
     the
    1.45
     this
    1.27
     each
    1.27
     their
    1.22
     how
    1.14
     its
    1.03
     your
    1.02
     creating
    1.02
    Activations Density 0.063%

    No Known Activations