© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5516
    Prev
    Next
    INDEX
    Explanations

    connect and links

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

    internet connection

    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
    बरोबर
    0.42
     ಮಿಶ್ರ
    0.40
    俘
    0.38
    齟
    0.35
    不满
    0.35
    યું
    0.35
    叔
    0.34
    蟀
    0.34
    omicide
    0.34
     महार
    0.34
    POSITIVE LOGITS
     connect
    4.22
    连接
    4.16
    connect
    4.06
     conect
    4.06
     CONNECT
    3.95
     connecting
    3.92
     Connect
    3.91
     연결
    3.84
     connection
    3.83
    連接
    3.83
    Activations Density 0.483%

    No Known Activations