© 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-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 13000
    Prev
    Next
    INDEX
    Explanations

    television and broadcasting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     брау
    0.64
     UNIX
    0.63
     非
    0.60
     Cupertino
    0.59
     स्थिति
    0.57
     reprint
    0.55
     Gateway
    0.55
     ổ
    0.55
     Oxford
    0.54
     injunctive
    0.54
    POSITIVE LOGITS
    テレビ
    1.23
     television
    1.14
    番組
    1.14
    Television
    1.13
    TV
    1.10
     방송
    1.10
     Television
    1.09
     telewiz
    1.08
     télévision
    1.05
    television
    1.03
    Activations Density 0.085%

    No Known Activations