© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 3547
    Prev
    Next
    INDEX
    Explanations

    descriptive terms and transportation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dateien
    0.47
     audiovisual
    0.44
    )}^{
    0.43
     opción
    0.43
     MERCHANT
    0.43
     sweetheart
    0.43
     नियंत्रित
    0.42
     এখনও
    0.42
     anisotrop
    0.42
     downregulated
    0.41
    POSITIVE LOGITS
    ઠવા
    0.40
     поне
    0.39
    䁂
    0.39
    ↵↵↵
    0.38
     اگ
    0.38
     hac
    0.38
    rust
    0.37
    ology
    0.37
    っぱり
    0.36
    ୁ
    0.36
    Activations Density 0.004%

    No Known Activations