© 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. 34-GEMMASCOPE-RES-131K
    7. 1175
    Prev
    Next
    INDEX
    Explanations

    Roder names and places

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

    This neuron detects personal names—especially the party names in legal case headings.

    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
    Typing
    -0.75
     Typing
    -0.73
    صلاح
    -0.71
     leek
    -0.65
    typing
    -0.65
     diminution
    -0.63
    菱
    -0.62
     شيئ
    -0.61
    Quiénes
    -0.61
    Determining
    -0.61
    POSITIVE LOGITS
    隹
    0.87
    spunk
    0.75
     Knudsen
    0.74
    girl
    0.73
    Nhi
    0.73
    γη
    0.72
     Equals
    0.72
    ⎫
    0.71
     awareness
    0.71
     enquanto
    0.71
    Activations Density 0.041%

    No Known Activations