© 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. 22-GEMMASCOPE-RES-131K
    4. 36435
    Prev
    Next
    INDEX
    Explanations

    comparing similar concepts

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

    The neuron is triggered by names of scientific or technical research domains (e.g. “climate change,” “biophysical dimensions,” “health sciences,” “environmental sciences”).

    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
    他们在
    -0.88
     isolado
    -0.82
     ديسمبر
    -0.81
    万美元
    -0.81
     „
    -0.81
     joka
    -0.80
    ?.
    -0.80
    *,
    -0.79
    Création
    -0.79
    ?,
    -0.77
    POSITIVE LOGITS
     analogous
    1.02
    Similar
    1.01
     Similarly
    0.97
     examples
    0.96
     similar
    0.96
    tlere
    0.92
    similar
    0.91
     Similar
    0.91
    الش
    0.90
     condiv
    0.90
    Activations Density 0.251%

    No Known Activations