© 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. 82670
    Prev
    Next
    INDEX
    Explanations

    action and state updates

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

    The neuron fires on code tokens containing the substring “rx” (e.g. rx, ngrx, rxjs).

    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
    promises
    -0.80
     giveaway
    -0.77
    ̽
    -0.77
    ⃛
    -0.76
    puede
    -0.76
     Jesucristo
    -0.75
    CONCLUSIONES
    -0.74
    同伴
    -0.74
     ilustracja
    -0.73
    ١
    -0.73
    POSITIVE LOGITS
     effect
    0.94
    ToAction
    0.87
     state
    0.87
     Action
    0.85
    Facade
    0.83
     effects
    0.82
     Effects
    0.81
     Dan
    0.80
     union
    0.79
    Effects
    0.79
    Activations Density 0.009%

    No Known Activations