© 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. 12183
    Prev
    Next
    INDEX
    Explanations

    philosophical concepts of being and existence

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

    The neuron specializes in detecting abstract ontology‐ and essence‐related philosophical terms.

    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
     carrinho
    -1.17
    ≅
    -1.15
     статистика
    -1.15
     to
    -1.13
     referrerpolicy
    -1.13
     zobac
    -1.10
    decoração
    -1.10
    挑戦
    -1.10
    sizeCache
    -1.09
    mlung
    -1.07
    POSITIVE LOGITS
     this
    1.30
     てき
    1.17
    tefan
    1.16
    埂
    1.13
     hadapan
    1.13
     you
    1.11
    :'',
    1.09
    :'/
    1.09
    this
    1.06
    Кру
    1.06
    Activations Density 0.032%

    No Known Activations