© 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-262K
    7. 43236
    Prev
    Next
    INDEX
    Explanations

    German "eine" followed by own/founded

    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_262k_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
     produtos
    0.61
    ujourd
    0.61
     productos
    0.60
     peuple
    0.58
     άνθρω
    0.58
     Leben
    0.57
     Produtos
    0.55
    閡
    0.55
    ictionnaire
    0.54
    setzen
    0.54
    POSITIVE LOGITS
    ة
    1.00
    ing
    0.80
    a
    0.74
    ింది
    0.62
     واحدة
    0.61
     была
    0.60
    Straße
    0.56
    ه
    0.55
    아
    0.55
     była
    0.53
    Activations Density 0.026%

    No Known Activations