© 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. 22-GEMMASCOPE-RES-131K
    7. 38305
    Prev
    Next
    INDEX
    Explanations

    RL graph or environment setup

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

    This neuron fires on mentions of the OpenAI Gym “BipedalWalker-v2” environment (i.e. the pieces of the “gym.make('BipedalWalker-v2')” identifier).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    
    -1.27
     kaos
    -1.26
     Lettres
    -1.14
     luxem
    -1.14
     diskon
    -1.13
    `{.
    -1.13
     دیدن
    -1.13
    izadores
    -1.12
     сс
    -1.11
     acrylique
    -1.09
    POSITIVE LOGITS
    rália
    1.27
    SafeAreaView
    1.27
    Ông
    1.22
     variaciones
    1.20
     širo
    1.20
    Đặc
    1.20
    nikahan
    1.18
    Màu
    1.18
     sağlar
    1.17
     Američ
    1.17
    Activations Density 0.009%

    No Known Activations