© 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. 223945
    Prev
    Next
    INDEX
    Explanations

    other than multilingual text

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

    museums and individuals

    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
    Ancient
    0.54
    History
    0.54
    S
    0.54
     as
    0.50
    Objectives
    0.49
    أ
    0.49
     History
    0.48
    J
    0.48
    Reasons
    0.47
    Million
    0.47
    POSITIVE LOGITS
    kę
    0.57
     ช่วง
    0.54
     ฝึก
    0.54
     कर
    0.52
    ować
    0.52
     طی
    0.52
     ਕਰਨ
    0.51
     折り
    0.51
    kort
    0.49
     แรง
    0.49
    Activations Density 0.001%

    No Known Activations