© 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. 223365
    Prev
    Next
    INDEX
    Explanations

    Australian Senate inquiry

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

    adhere to safety standards

    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
    Etiam
    0.52
     Bakın
    0.51
     छोड़
    0.49
     왼
    0.48
     ቀላል
    0.48
     Boż
    0.48
     njegove
    0.47
     alleviate
    0.47
    డ్‌
    0.47
     ње
    0.47
    POSITIVE LOGITS
        
    0.46
    mathrm
    0.44
     eller
    0.43
    চি
    0.42
    لیسی
    0.42
    身
    0.41
    距离
    0.39
    "@
    0.39
    或是
    0.39
    ূল্য
    0.39
    Activations Density 0.000%

    No Known Activations