© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78788
    Prev
    Next
    INDEX
    Explanations

    Pro Wrestling Hall of Fame

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

    The neuron spotlights combat‐sports reportage language—especially professional‐wrestling terms and match commentary.

    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
     dévou
    -0.85
     пръ
    -0.82
     Entfernung
    -0.81
    لسی
    -0.79
     ratusan
    -0.79
    yati
    -0.79
    ému
    -0.77
    labilir
    -0.77
     deaths
    -0.76
     tubular
    -0.75
    POSITIVE LOGITS
    づく
    0.96
     wrist
    0.78
    ‡
    0.76
    lock
    0.76
     worked
    0.75
     Irish
    0.73
     hanggang
    0.73
     exchanged
    0.72
     bekerja
    0.72
     nice
    0.71
    Activations Density 0.002%

    No Known Activations