© 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. 91919
    Prev
    Next
    INDEX
    Explanations

    time and date

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

    uncovers limitations and discoveries

    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
     Atual
    0.52
     GetAll
    0.49
    ق
    0.49
     Noor
    0.48
    style
    0.48
     personagens
    0.48
    Сан
    0.48
    GetAll
    0.47
     Parece
    0.47
    ineed
    0.47
    POSITIVE LOGITS
     disrupting
    0.54
     transforming
    0.48
     profitable
    0.45
     탁
    0.44
     Chichester
    0.44
     previously
    0.43
     subtracted
    0.43
    isVideoRecording
    0.43
    တစ်ခု
    0.43
     ጣ
    0.43
    Activations Density 0.004%

    No Known Activations