© 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. 34-GEMMASCOPE-RES-131K
    7. 94080
    Prev
    Next
    INDEX
    Explanations

    Queen of

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

    The neuron fires on named‐entity tokens and list‐style markers—proper names, titles, headings, and numeric entries.

    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
    日目
    -0.85
    ulli
    -0.85
    PoolSize
    -0.73
    ༽
    -0.71
    љено
    -0.70
    culos
    -0.70
    ocha
    -0.69
    鏢
    -0.68
    Arkansas
    -0.68
    っちゃ
    -0.68
    POSITIVE LOGITS
     Freddie
    1.81
     Bohemian
    1.45
    Freddie
    1.37
     Queen
    1.34
     Mercury
    1.27
    Queen
    1.20
    フレ
    1.09
     QUEEN
    1.09
    Mercury
    1.04
     bohemian
    1.04
    Activations Density 0.011%

    No Known Activations