© 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. 90744
    Prev
    Next
    INDEX
    Explanations

    villain or antagonist

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

    The neuron strongly activates on named entities—especially person names, character names, and other capitalized titles.

    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
    Ԁ
    -0.98
     Optimize
    -0.94
     superstars
    -0.93
     optimize
    -0.93
    retten
    -0.92
    ⅾ
    -0.90
     optimizing
    -0.83
    бля
    -0.82
    PreferredItem
    -0.82
     assaulted
    -0.82
    POSITIVE LOGITS
     villain
    3.53
     villains
    3.05
     antagonist
    2.80
    villain
    2.47
     evil
    2.45
     antagonists
    2.36
     villa
    2.25
     Villain
    2.20
    evil
    2.03
    villa
    2.00
    Activations Density 0.050%

    No Known Activations