© 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. 7016
    Prev
    Next
    INDEX
    Explanations

    McDonnell Douglas, EL, 2, CHF, sq

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

    project LF

    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
    ᐱ
    0.40
    InteropServices
    0.40
    ◝
    0.38
    甑
    0.38
    龜
    0.36
    ⦕
    0.35
    ㈡
    0.34
    कामना
    0.34
    ইয়া
    0.34
    莞
    0.33
    POSITIVE LOGITS
     MF
    3.08
    <0xA3>
    2.89
    MF
    2.83
     PF
    2.81
     LF
    2.80
     HF
    2.78
     VF
    2.78
     SF
    2.72
     TF
    2.70
     BF
    2.70
    Activations Density 0.418%

    No Known Activations