© 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. 102206
    Prev
    Next
    INDEX
    Explanations

    telecom company, revenue, holding

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

    the word “telecom,” i.e. occurrences of the term referring to telecommunications contexts or companies.

    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
     —
    -3.06
     Now
    -2.13
     ganze
    -2.06
     \
    -2.06
     они
    -2.06
     أصبح
    -2.03
    她就
    -2.03
    ココ
    -1.97
     Теперь
    -1.96
    ！）
    -1.95
    POSITIVE LOGITS
    n
    3.58
    s
    3.44
    .
    2.77
    詎
    2.69
    the
    2.53
    🌃
    2.48
    r
    2.39
    Ꮂ
    2.38
    ༷
    2.33
    鬈
    2.33
    Activations Density 0.002%

    No Known Activations