© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101004
    Prev
    Next
    INDEX
    Explanations

    rights, claims, and entitlements

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

    This neuron detects formal legal‐language cues indicating rights, entitlements, authorities, obligations, or invalidity in statutes, contracts, or court texts.

    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
     what
    -1.65
     how
    -1.58
    ẹo
    -1.57
     adverten
    -1.55
     a
    -1.53
    ﹶ
    -1.52
    什么呢
    -1.52
    .},
    -1.48
     hjemmes
    -1.47
     dominio
    -1.45
    POSITIVE LOGITS
     question
    1.41
     seulement
    1.41
     Assuming
    1.35
    しまって
    1.28
     esche
    1.27
     Either
    1.27
     Whether
    1.27
     ไม่มี
    1.25
     facades
    1.25
     assert
    1.22
    Activations Density 0.025%

    No Known Activations