© 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. 204970
    Prev
    Next
    INDEX
    Explanations

    using Bluetooth

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

    exposing complex sexual taboos

    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
    থায়
    0.43
    షణ
    0.43
     సూపర్
    0.42
    с
    0.42
    рос
    0.41
    fueled
    0.41
    do
    0.41
     optimist
    0.41
    爾
    0.41
    ТИ
    0.40
    POSITIVE LOGITS
     exposing
    0.46
     भ्रष्टाचार
    0.46
     sprzedaży
    0.45
     trả
    0.45
     przep
    0.45
     አስ
    0.44
    ào
    0.42
    বলী
    0.42
    オペ
    0.42
     chào
    0.41
    Activations Density 0.001%

    No Known Activations