© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16184
    Prev
    Next
    INDEX
    Explanations

    introducing a reason

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

    explaining causality with because

    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_16k_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
    ૧
    0.93
     поради
    0.88
     listy
    0.86
    ⒈
    0.84
    １
    0.82
    ।
    0.82
    ש
    0.82
    Have
    0.82
     và
    0.82
     podem
    0.81
    POSITIVE LOGITS
    ↵↵
    1.09
    :
    1.05
    ή
    1.02
    ↵
    0.90
    个
    0.89
    ী
    0.87
    কে
    0.85
    ة
    0.83
    ,
    0.82
    ü
    0.76
    Activations Density 1.690%

    No Known Activations