© 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. 91183
    Prev
    Next
    INDEX
    Explanations

    submission wins

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

    This neuron fires on text describing mixed martial arts fighters—their professional “mixed martial artist” bios, fight divisions, and competition details.

    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
     Disney
    -0.83
    ೪
    -0.80
     anh
    -0.80
    婁
    -0.80
    скільки
    -0.80
     possam
    -0.79
    czka
    -0.79
    robat
    -0.79
    Kirchen
    -0.79
     Alamo
    -0.76
    POSITIVE LOGITS
     Fedor
    0.88
     Submission
    0.83
     submission
    0.79
     Submissions
    0.79
     tena
    0.76
    filler
    0.75
    submission
    0.75
    nancy
    0.73
    ня
    0.73
     Shoot
    0.72
    Activations Density 0.037%

    No Known Activations