© 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. 84218
    Prev
    Next
    INDEX
    Explanations

    Phoenix Wright objections

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

    The neuron fires on capitalized named entities—especially video game titles, character names, and related proper nouns.

    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
    *}
    
    -0.71
     Sozial
    -0.71
     autorités
    -0.71
     anten
    -0.71
     tủ
    -0.71
     gol
    -0.70
     notified
    -0.69
     derogatory
    -0.69
     unto
    -0.69
    zik
    -0.68
    POSITIVE LOGITS
     Objection
    1.10
     Psyche
    0.93
     objections
    0.91
     objection
    0.88
     Wright
    0.86
    Wright
    0.83
     WRIGHT
    0.81
     Yat
    0.79
     Layton
    0.79
     gallery
    0.79
    Activations Density 0.029%

    No Known Activations