© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5478
    Prev
    Next
    INDEX
    Explanations

    . ? ”

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

    ** followed by *

    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
    )」
    0.42
    queira
    0.39
    ربية
    0.38
    ️⃣
    0.38
    ⃣
    0.38
    )](
    0.38
    byshire
    0.37
    dometer
    0.37
    veen
    0.36
    yers
    0.36
    POSITIVE LOGITS
    ↵
    0.50
     //
    0.41
     ;
    0.39
              
    0.39
     Wealth
    0.37
       
    0.37
        
    0.36
     FIXME
    0.35
    */
    0.35
    ⁠
    0.35
    Activations Density 0.029%

    No Known Activations