© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91563
    Prev
    Next
    INDEX
    Explanations

    TNA wrestling names

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

    The neuron is triggered by all-caps tokens—especially acronym-style or title-style uppercase sequences (e.g. “TNA,” “AAA,” “STAR”).

    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
     Akron
    -0.84
     Chandigarh
    -0.84
     Cebu
    -0.82
    №
    -0.82
     Swindon
    -0.80
    BTC
    -0.79
     Gohan
    -0.78
    การ
    -0.75
    SQLite
    -0.74
     Tagore
    -0.73
    POSITIVE LOGITS
     TNA
    0.99
     IMPACT
    0.92
     Impact
    0.81
     impact
    0.81
    SharedModule
    0.77
    かし
    0.77
     Wittenberg
    0.76
    ⽬
    0.75
    ungal
    0.73
     pensamos
    0.73
    Activations Density 0.011%

    No Known Activations