© 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. 67650
    Prev
    Next
    INDEX
    Explanations

    names followed by places or roles

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

    This neuron activates on capitalized title‐ or headline‐style tokens—i.e. words in article headings or subheadings.

    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
    🗿
    -0.92
    🧍
    -0.89
     their
    -0.85
    ：（
    -0.84
    fasterxml
    -0.82
     amar
    -0.81
     wyn
    -0.80
     dekorasi
    -0.79
     بھی
    -0.78
    dof
    -0.78
    POSITIVE LOGITS
     columnist
    1.13
     meint
    1.07
     suí
    1.02
     thoughts
    1.02
     nạ
    0.99
     поможет
    0.98
     armazenamento
    0.96
     correta
    0.93
     didn
    0.93
     shouldn
    0.92
    Activations Density 0.123%

    No Known Activations