© 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. 57470
    Prev
    Next
    INDEX
    Explanations

    Pokemon and technical terms

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

    The neuron strongly activates on named entities and other capitalized or distinctive proper nouns (e.g., Pokémon names, character names, product or place names).

    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
    opley
    -0.85
     slime
    -0.85
    hazi
    -0.83
    нологі
    -0.80
    Agency
    -0.79
    を外
    -0.79
     Cyril
    -0.78
    leetcode
    -0.78
     Guerrero
    -0.77
     Agency
    -0.76
    POSITIVE LOGITS
    Kro
    0.74
     marinho
    0.69
    valier
    0.69
    侑
    0.67
    Fract
    0.66
    Eles
    0.66
     elétrico
    0.64
     uporab
    0.63
    هره
    0.63
     diplom
    0.62
    Activations Density 0.004%

    No Known Activations