© 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. 60821
    Prev
    Next
    INDEX
    Explanations

    law/legal contexts

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

    The neuron is triggered by statutory “possession/distribution” verbs (e.g. possess, produced, disseminate) in legal‐text provisions.

    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
     القلب
    -0.79
     bootstra
    -0.77
    渎
    -0.76
     ‐
    -0.75
     bong
    -0.75
    Gord
    -0.74
    rime
    -0.73
     simon
    -0.73
     клави
    -0.72
     MULTIP
    -0.72
    POSITIVE LOGITS
     persons
    1.09
     premises
    1.01
     Benedetto
    0.87
     places
    0.87
     proclaimed
    0.87
     pratique
    0.85
     articles
    0.85
     any
    0.85
     eenige
    0.84
    遊戯
    0.84
    Activations Density 0.019%

    No Known Activations