© 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. 145100
    Prev
    Next
    INDEX
    Explanations

    features tax, meet the, tend to

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

    foreign language or abstract concepts

    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
    ᥣ
    0.50
     Initiative
    0.48
     iniciativas
    0.47
    தியை
    0.47
    ولت
    0.46
    泮
    0.46
     Pattes
    0.45
     부분을
    0.45
     Palazzo
    0.45
    魄
    0.45
    POSITIVE LOGITS
    lain
    0.46
    AB
    0.43
    LIKE
    0.43
    Almost
    0.43
     [--
    0.43
    контро
    0.43
    lii
    0.41
     عمرو
    0.41
     almost
    0.40
    TRAN
    0.40
    Activations Density 0.001%

    No Known Activations