© 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. 172433
    Prev
    Next
    INDEX
    Explanations

    Chinese continent

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

    orbiting the Earth

    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
    东南
    0.49
    玑
    0.49
     सुरु
    0.47
    aining
    0.47
    ensation
    0.46
    蝈
    0.45
     बुलंद
    0.45
    rie
    0.44
    沨
    0.44
     Meanwhile
    0.44
    POSITIVE LOGITS
     slij
    0.49
     suaves
    0.47
     freezed
    0.47
     encont
    0.46
     perdu
    0.46
     Cient
    0.46
     jedan
    0.46
    シーズ
    0.46
     perioada
    0.45
    を使用
    0.44
    Activations Density 0.001%

    No Known Activations