© 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. 22-GEMMASCOPE-RES-131K
    7. 9823
    Prev
    Next
    INDEX
    Explanations

    ownership and inheritance

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

    The neuron is keyed to passages describing provenance or ownership history—mentions of former owners, inheritance, collections, dates held, 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_22/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
    >,</
    -1.27
     resultado
    -1.03
     solution
    -1.02
    fasterxml
    -0.99
     positioned
    -0.99
     الرجال
    -0.96
    !="")
    -0.96
    BRIDGE
    -0.96
     hybride
    -0.96
     устрой
    -0.94
    POSITIVE LOGITS
     after
    1.25
     после
    1.20
     then
    1.17
    Затем
    1.16
    After
    1.14
    После
    1.13
    を経て
    1.11
     ownership
    1.08
     לאחר
    1.07
    ื้อ
    1.06
    Activations Density 0.048%

    No Known Activations