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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1320
    Prev
    Next
    INDEX
    Explanations

    news agency reports

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

    Reuters and BBC news

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Supernatural
    0.38
     Prothorax
    0.38
     Frog
    0.38
     Pancake
    0.38
     Quadrup
    0.37
    导入
    0.37
     Adventures
    0.37
    {\"
    0.37
    规划
    0.36
     Primitive
    0.36
    POSITIVE LOGITS
    記者
    0.98
     Xinhua
    0.97
     correspondent
    0.95
    Xinhua
    0.94
     Correspondent
    0.94
    news
    0.91
     reporter
    0.91
     IANS
    0.89
     NEWS
    0.89
    報道
    0.88
    Activations Density 0.051%

    No Known Activations