© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71896
    Prev
    Next
    INDEX
    Explanations

    rights grant

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

    The neuron fires on occurrences of the word “rights.”

    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
     was
    -2.95
    (
    -2.52
     –
    -2.52
    ["_
    -2.33
     —
    -2.27
     “
    -2.20
    [
    -2.16
     Not
    -2.14
    %。
    -2.14
     multitude
    -2.13
    POSITIVE LOGITS
    趼
    3.14
    
    2.75
     帅气
    2.53
    锨
    2.52
    CÓMO
    2.48
     difficoltà
    2.45
    ه
    2.45
     bús
    2.45
    ㌧
    2.41
    Ventajas
    2.38
    Activations Density 0.163%

    No Known Activations