© 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. 34-GEMMASCOPE-RES-131K
    4. 107514
    Prev
    Next
    INDEX
    Explanations

    naturally aspirated

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

    The neuron fires on numeric technical specifications—especially engine power, displacement, and similar unit‐based measurements.

    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
    륙
    -0.72
    сные
    -0.72
     solitude
    -0.71
    ۖ
    -0.70
     Partridge
    -0.70
    haz
    -0.68
     caza
    -0.68
    гина
    -0.68
    oyer
    -0.68
    檔案
    -0.67
    POSITIVE LOGITS
     naturally
    2.50
     natural
    2.45
    自然
    2.23
    naturally
    2.16
     Natural
    2.11
     Naturally
    2.11
    natural
    2.09
    Natural
    2.09
     aspir
    2.08
     NATURAL
    2.06
    Activations Density 0.026%

    No Known Activations