© 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. 73808
    Prev
    Next
    INDEX
    Explanations

    give or send message

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

    This neuron detects long runs of whitespace (indentation or large spans of spaces) in the 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
    urai
    -0.84
    崩溃
    -0.79
     Grub
    -0.77
     id
    -0.76
     håller
    -0.76
     कहा
    -0.75
    cul
    -0.75
     pasaron
    -0.72
     reagieren
    -0.71
    tileno
    -0.70
    POSITIVE LOGITS
     send
    1.02
     give
    0.91
     Give
    0.84
    loin
    0.84
     endIndex
    0.84
    sneaker
    0.84
     sendMessage
    0.84
     message
    0.83
    send
    0.83
     grant
    0.82
    Activations Density 0.003%

    No Known Activations