© 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. 38134
    Prev
    Next
    INDEX
    Explanations

    always

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

    software and services

    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
    冬天
    0.51
    했는데
    0.47
    dete
    0.47
    Hei
    0.47
    tidal
    0.45
    揀
    0.45
    ramble
    0.44
     caiu
    0.44
     erano
    0.43
    詳細
    0.43
    POSITIVE LOGITS
     toujours
    0.47
     всегда
    0.46
     Ghosh
    0.45
     zawsze
    0.44
    💼
    0.44
     ہمیشہ
    0.43
     завжди
    0.42
     අවශ්‍ය
    0.42
     शोषण
    0.41
     গ্রস্থ
    0.41
    Activations Density 0.000%

    No Known Activations