© 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. 49976
    Prev
    Next
    INDEX
    Explanations

    gyms and challenges

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

    This neuron responds to uncommon or rare subword tokens (those with high vocabulary indices), such as longer or less frequent words.

    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
    țion
    -0.81
     sacro
    -0.78
    cidos
    -0.75
    spiele
    -0.74
     dile
    -0.73
     Golfo
    -0.73
    utiny
    -0.73
     Uti
    -0.71
    UserLogin
    -0.71
     فروش
    -0.70
    POSITIVE LOGITS
     gym
    1.12
     challenge
    1.01
     Challenge
    0.94
     Gym
    0.93
    chall
    0.88
     challenger
    0.85
     gyms
    0.84
    challenge
    0.81
    gym
    0.81
     Victory
    0.77
    Activations Density 0.014%

    No Known Activations