© 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. 202852
    Prev
    Next
    INDEX
    Explanations

    rhymes, fireworks, microphone, process, round, Owner, pool

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

    international words and phrases

    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
     fintech
    0.43
    ='',
    0.39
    ''_
    0.39
     кода
    0.39
     facades
    0.38
     datasets
    0.37
     universes
    0.37
     JONES
    0.36
     specimens
    0.36
     島
    0.36
    POSITIVE LOGITS
     वॉइस
    0.50
    सभी
    0.49
    Всім
    0.47
     nhạc
    0.47
     Wohl
    0.45
     всем
    0.45
     Conservatives
    0.44
     Otros
    0.44
     thankfully
    0.43
     geht
    0.42
    Activations Density 0.002%

    No Known Activations