© 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. 102335
    Prev
    Next
    INDEX
    Explanations

    with the

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

    multilingual contexts or non-English words

    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
    慮
    0.45
     Nore
    0.43
     Borrow
    0.43
     richly
    0.43
    岭
    0.43
     cherish
    0.42
    unnels
    0.42
    ச்செய
    0.42
    ki
    0.42
    ku
    0.42
    POSITIVE LOGITS
     పార్టీ
    0.47
     valet
    0.42
    Baltimore
    0.41
     dampers
    0.41
    ründ
    0.40
     victime
    0.40
     perpetrator
    0.39
     perpetrators
    0.38
     //[
    0.38
     volt
    0.38
    Activations Density 0.000%

    No Known Activations