© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81754
    Prev
    Next
    INDEX
    Explanations

    Targaryen, Search This, /* globals, Fancy Dress, Q:

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

    The neuron detects mentions of specific proper names and titles of characters (especially royal or noble figures).

    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
     formaldehyde
    -0.70
     vaccinations
    -0.70
    ikom
    -0.70
     Pullman
    -0.69
    itní
    -0.68
    大神
    -0.68
    ッカ
    -0.67
     horizontally
    -0.65
     Salvation
    -0.64
    五百
    -0.64
    POSITIVE LOGITS
     Targ
    1.78
     dragon
    1.19
     dragons
    1.07
    Dragon
    0.99
     Dragons
    0.95
     Dragon
    0.93
     DRAGON
    0.91
     targ
    0.90
    Dragons
    0.89
    dragon
    0.88
    Activations Density 0.011%

    No Known Activations