© 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. 128902
    Prev
    Next
    INDEX
    Explanations

    import not working

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

    Development documentation versions

    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
     Пере
    0.48
     Δεν
    0.47
     Ві
    0.47
     Π
    0.47
     Пів
    0.46
    dirs
    0.46
     その他
    0.44
     Ι
    0.44
     نمی
    0.44
     Ар
    0.44
    POSITIVE LOGITS
     kvinn
    0.54
     crece
    0.53
     gallant
    0.49
    巧克力
    0.48
    觅
    0.48
     congressional
    0.47
     adott
    0.47
     चॉकलेट
    0.47
    ർ
    0.46
    șt
    0.46
    Activations Density 0.001%

    No Known Activations