© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13969
    Prev
    Next
    INDEX
    Explanations

    deals with videos

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

    The neuron detects occurrences of the word “video” (including its plural form “videos”).

    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
    \"
    -2.72
     \
    -2.66
     ที่
    -2.52
    0
    -2.52
    The
    -2.50
    ～～
    -2.42
    ↵↵
    -2.36
     самая
    -2.34
     и
    -2.31
     \"
    -2.30
    POSITIVE LOGITS
    蔸
    2.94
    鬭
    2.84
    这个世界
    2.84
    鯪
    2.66
    ðsíða
    2.59
    鹇
    2.53
    鮓
    2.45
    苼
    2.42
    甞
    2.28
    쨩
    2.28
    Activations Density 0.007%

    No Known Activations