© 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. 31-GEMMASCOPE-2-RES-262K
    7. 210026
    Prev
    Next
    INDEX
    Explanations

    successful transplants

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

    structured headings and lists

    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_262k_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
     autonom
    0.46
     চালাতে
    0.45
     изначально
    0.44
    𝘱
    0.43
     embarking
    0.42
     utilisant
    0.42
     laiss
    0.42
    
    0.42
     आवृत्ति
    0.41
    ธาร
    0.40
    POSITIVE LOGITS
    Cache
    0.49
    能
    0.47
     RE
    0.45
    目
    0.45
    清除
    0.42
    ine
    0.42
    尾
    0.41
     Cache
    0.41
     readonly
    0.41
    Others
    0.41
    Activations Density 0.001%

    No Known Activations