© 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. 88857
    Prev
    Next
    INDEX
    Explanations

    research study

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

    reflection and its translations

    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
     xsi
    0.54
     चीज़
    0.50
     کرام
    0.48
     ভাষায়
    0.48
    𒁀
    0.48
    edics
    0.47
    𝙢
    0.47
     ನೆ
    0.47
    ⃙
    0.47
     monasteries
    0.46
    POSITIVE LOGITS
    c
    0.54
    还没
    0.45
    反射
    0.45
    x
    0.44
    产生
    0.44
     haven
    0.43
    न्देल
    0.43
    nv
    0.43
     उतनी
    0.42
     প্রতিফল
    0.42
    Activations Density 0.001%

    No Known Activations