© 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. 26100
    Prev
    Next
    INDEX
    Explanations

    multilingual text or diverse languages

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

    **schedAlwaystest

    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
    響
    0.52
    ствует
    0.51
    textrm
    0.49
    正好
    0.49
    िलो
    0.48
     lobbyists
    0.48
    無法
    0.48
    ный
    0.47
    リスト
    0.46
    游
    0.46
    POSITIVE LOGITS
    .’
    0.51
     وك
    0.51
     интернет
    0.49
     Интернет
    0.49
     ఎ
    0.49
     ඉද
    0.48
     éché
    0.48
     ಅದನ್ನು
    0.47
     változat
    0.47
    កំណ
    0.46
    Activations Density 0.000%

    No Known Activations