© 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. 114800
    Prev
    Next
    INDEX
    Explanations

    refund

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

    curious to understand

    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
    ante
    0.47
     amph
    0.47
     Vedas
    0.46
    *
    0.44
    ཾ
    0.44
     elementy
    0.43
    fixed
    0.42
     novi
    0.42
     invent
    0.42
    verse
    0.41
    POSITIVE LOGITS
    留学
    0.50
    లు
    0.48
    槽
    0.45
    的一些
    0.45
    WARF
    0.45
    ઈએ
    0.44
    桃
    0.44
    上
    0.44
    섰
    0.44
     包括
    0.43
    Activations Density 0.002%

    No Known Activations