© 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. 87171
    Prev
    Next
    INDEX
    Explanations

    furnished to

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

    The neuron strongly activates on occurrences of the word “furnished” (especially in phrases like “furnished to”) in license or legal‐permission texts.

    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
    鹟
    -3.08
    鰱
    -3.00
     tekno
    -2.98
    ㍑
    -2.81
    毟
    -2.78
    
    -2.75
    熥
    -2.72
     dili
    -2.72
     우리
    -2.64
    Ꮴ
    -2.64
    POSITIVE LOGITS
    ↵↵
    3.91
     When
    3.08
    …
    2.63
    –
    2.59
     but
    2.50
    …..
    2.48
     
    2.48
     Those
    2.45
    m
    2.45
     –
    2.42
    Activations Density 0.004%

    No Known Activations