© 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. 49531
    Prev
    Next
    INDEX
    Explanations

    light bar

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

    focuses on affordability and level

    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
     但是
    0.52
     ワン
    0.49
     다만
    0.47
     那麼
    0.47
     superiori
    0.47
     totiž
    0.46
    '],
    0.46
    但是
    0.45
     الجديد
    0.45
     hochwert
    0.45
    POSITIVE LOGITS
    is
    0.57
    agis
    0.54
    Есть
    0.53
    끔
    0.52
    னி
    0.50
    are
    0.50
     concentración
    0.49
    IsMethod
    0.49
    datos
    0.48
    ěř
    0.48
    Activations Density 0.000%

    No Known Activations