© 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
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4222
    Prev
    Next
    INDEX
    Explanations

    location phrases

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

    co-working spaces

    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
    )";
    0.44
    )、
    0.42
    /";
    0.41
    rahman
    0.38
                         
    0.38
    ;",
    0.38
     一般
    0.38
    /")
    0.37
    "<<
    0.37
     表
    0.36
    POSITIVE LOGITS
     Casa
    0.91
     Z
    0.85
     Aqua
    0.82
     Blue
    0.82
     Dragonfly
    0.82
     Sky
    0.81
     M
    0.79
     Dragon
    0.78
     Crazy
    0.78
     La
    0.77
    Activations Density 1.296%

    No Known Activations