© 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. 10-GEMMASCOPE-RES-131K
    4. 130933
    Prev
    Next
    INDEX
    Explanations

    video formats like mp4, mov, avi

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

    The neuron detects tokens that are part of multimedia file‐format identifiers—especially the numeric components of extensions (e.g. “4” in “mp4,” “3” in “3gp,” numeric suffixes, and similar video/audio format strings).

    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
     in
    -1.71
    ie
    -1.59
    人的
    -1.52
    in
    -1.51
    os
    -1.44
    ons
    -1.34
     Consejos
    -1.33
    ją
    -1.32
     looks
    -1.31
     Diarsipkan
    -1.31
    POSITIVE LOGITS
    庹
    1.63
    焌
    1.61
    
    1.54
     shew
    1.52
     stratég
    1.51
    quisar
    1.51
    梃
    1.48
    Новые
    1.47
     animados
    1.47
     vistos
    1.46
    Activations Density 0.013%

    No Known Activations