© 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. 34-GEMMASCOPE-RES-131K
    7. 90429
    Prev
    Next
    INDEX
    Explanations

    possession, occupation, use

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

    The neuron primarily detects technical legal‐definition terms (e.g. “average,” “water mark,” “constituted,” “bed,” “bank,” “floatsam,” “jetsam,” 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
     obrig
    -0.84
    enlace
    -0.79
     syntactic
    -0.72
     synapse
    -0.72
    Comentários
    -0.70
    ChildScrollView
    -0.70
    icionar
    -0.70
    immortal
    -0.69
     targets
    -0.69
    ^{*
    -0.69
    POSITIVE LOGITS
     enjoyment
    1.41
     possession
    1.19
    Enjoy
    1.15
     occupation
    1.12
    enjoy
    1.11
     ENJOY
    1.07
     use
    1.05
     occupancy
    1.02
     usage
    1.02
     occup
    1.01
    Activations Density 0.012%

    No Known Activations