© 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. 67238
    Prev
    Next
    INDEX
    Explanations

    multiple choices or combinations

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

    This neuron responds to technical terms that describe functional roles or theoretical models (e.g. “function,” “role,” “models,” “prediction,” “vigilance”) in a neuroscience context.

    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
    わかる
    -1.08
     tuong
    -0.99
    setPreferred
    -0.94
     argento
    -0.90
     feel
    -0.88
    黽
    -0.87
    お試し
    -0.87
     desirable
    -0.83
    センサー
    -0.81
     aproximativ
    -0.81
    POSITIVE LOGITS
     plutôt
    1.32
    むしろ
    1.16
     instead
    1.14
     وأن
    1.09
     inkább
    1.07
     only
    1.05
     invece
    1.01
     merely
    0.95
     kabát
    0.94
    explique
    0.94
    Activations Density 0.104%

    No Known Activations