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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13667
    Prev
    Next
    INDEX
    Explanations

    use and operation

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

    usage in various languages

    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_31_width_16k_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
    交渉
    0.47
     cheaply
    0.46
    彥
    0.46
     কারো
    0.46
    
    0.44
    𝖽
    0.44
     細胞
    0.44
    що
    0.43
    bara
    0.43
     dentures
    0.43
    POSITIVE LOGITS
     Usage
    1.09
     usage
    1.02
     użyt
    0.96
    ใช้งาน
    0.92
    Usage
    0.90
     kullanım
    0.88
     uso
    0.85
     penggunaan
    0.84
    usage
    0.83
     käyttö
    0.82
    Activations Density 0.450%

    No Known Activations