© 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. 15097
    Prev
    Next
    INDEX
    Explanations

    depends on what follows

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

    based on definitions

    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
     घेऊन
    0.41
     جهت
    0.40
     costume
    0.38
     pentru
    0.38
     apporter
    0.38
    hele
    0.37
     ekki
    0.37
     ለ
    0.37
     své
    0.37
     nhiên
    0.37
    POSITIVE LOGITS
    取决于
    0.72
    derive
    0.68
    是通过
    0.68
    =((
    0.68
     =(
    0.64
     depends
    0.63
     dựa
    0.63
     basado
    0.62
     Depends
    0.59
     basada
    0.58
    Activations Density 0.180%

    No Known Activations