© 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. 181179
    Prev
    Next
    INDEX
    Explanations

    data protection officers

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

    rocking chair

    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
    ito
    0.54
    :
    0.49
     truffle
    0.47
    ij
    0.46
    ers
    0.45
     siempre
    0.45
     crispy
    0.44
     statue
    0.44
    adorable
    0.44
     pog
    0.44
    POSITIVE LOGITS
    赜
    0.52
    ดาว
    0.48
    军队
    0.45
    সম্পাদক
    0.44
     públicas
    0.43
    বায়
    0.43
    ค้า
    0.42
    ейчас
    0.42
    ുപത്രി
    0.42
    配置文件
    0.42
    Activations Density 0.004%

    No Known Activations