© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5968
    Prev
    Next
    INDEX
    Explanations

    lists originating from

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

    originating from various languages

    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_53_width_65k_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
     從
    0.65
     从
    0.62
    पासून
    0.61
    从
    0.57
    થી
    0.54
    Von
    0.53
    從小
    0.52
    從
    0.52
     થી
    0.50
     Από
    0.50
    POSITIVE LOGITS
    来自
    1.67
    來自
    1.66
    来自于
    1.45
     hailing
    1.39
     provenienti
    1.23
     belonging
    1.23
     provenant
    1.22
     sourced
    1.15
     originating
    1.15
     berasal
    1.11
    Activations Density 0.089%

    No Known Activations