© 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. 10-GEMMASCOPE-RES-131K
    7. 9373
    Prev
    Next
    INDEX
    Explanations

    pathogenic bacteria, refrigerant, Punjabi documentaries, plumb device

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

    scientific or technical terms related to pathogens, bacteria, refrigerants, and geographical locations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on uncommon, domain-specific nouns or technical terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    0
    -4.75
    5
    -4.19
    2
    -4.06
    r
    -3.98
    8
    -3.92
    --
    -3.91
    n
    -3.88
    The
    -3.81
    9
    -3.77
     “
    -3.64
    POSITIVE LOGITS
    馓
    3.53
    嗵
    3.52
    踽
    3.34
    檍
    3.28
    🧌
    3.19
    
    3.11
    🩻
    3.11
    塲
    3.11
    甍
    3.09
    愎
    3.06
    Activations Density 0.039%

    No Known Activations