© 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. 123463
    Prev
    Next
    INDEX
    Explanations

    television abbreviations

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

    The neuron fires on instances of the token “TV” (e.g. in television station call‐signs or the abbreviation “TV”).

    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
     offizielle
    -2.97
    愎
    -2.61
     vollständige
    -2.59
    CHREIB
    -2.56
     wichtige
    -2.53
     erfolgreiche
    -2.52
     ehemalige
    -2.47
    ↵
    -2.45
    ｢
    -2.31
     zusätzliche
    -2.30
    POSITIVE LOGITS
    a
    4.34
    ed
    3.83
    e
    3.48
    o
    3.20
    ’
    3.19
    u
    2.92
    ı
    2.91
    f
    2.84
    )
    2.83
    y
    2.81
    Activations Density 0.006%

    No Known Activations