© 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. 65726
    Prev
    Next
    INDEX
    Explanations

    rights to be informed

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

    The neuron activates on mentions of “the right to…” or similar human, social, and economic rights formulations.

    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
     imidlertid
    -1.22
    ꗃ
    -1.21
     gebruiken
    -1.20
     extremamente
    -1.20
     ноябре
    -1.19
     szuka
    -1.18
    nitř
    -1.16
    sterreich
    -1.16
     flexível
    -1.16
    howto
    -1.13
    POSITIVE LOGITS
    </h3>
    1.30
    <strong>
    1.23
     حتی
    1.20
     даже
    1.20
     even
    1.16
    unitOfWork
    1.16
    ()+"
    1.14
    //!
    1.14
    ACION
    1.13
     उनके
    1.10
    Activations Density 0.074%

    No Known Activations