© 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. 81477
    Prev
    Next
    INDEX
    Explanations

    XML and code blocks

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

    The neuron is sensitive to all‐caps words or phrases (e.g. the uppercase license/disclaimer text).

    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
     Physical
    -0.74
     آل
    -0.73
     خودم
    -0.72
    睞
    -0.71
     Bacterial
    -0.71
     iprot
    -0.71
    克兰
    -0.70
     glyphicon
    -0.70
     nutritious
    -0.69
    entiel
    -0.68
    POSITIVE LOGITS
    pixel
    0.84
    dataset
    0.81
     VR
    0.81
    oplayer
    0.79
    Dataset
    0.76
    VR
    0.73
    countdown
    0.71
    kod
    0.70
    encoder
    0.70
    Suspense
    0.68
    Activations Density 0.004%

    No Known Activations