© 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. 10421
    Prev
    Next
    INDEX
    Explanations

    discover, report, discover

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

    lists and separators

    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
    위를
    0.50
    ᅱ
    0.39
    인이
    0.39
    annya
    0.38
     guide
    0.38
     predict
    0.38
     invent
    0.38
     pave
    0.38
    дото
    0.37
     INSPIRE
    0.37
    POSITIVE LOGITS
     Featuring
    0.43
     আবি
    0.41
    மனை
    0.39
     Gebrauch
    0.38
    锄
    0.38
    ខ្ញ
    0.38
     আবির্ভাব
    0.38
    Featuring
    0.37
    ➺
    0.37
     বয়
    0.37
    Activations Density 0.000%

    No Known Activations