© 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. 224825
    Prev
    Next
    INDEX
    Explanations

    right to object

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

    Shanghai dumplings cup

    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
    📐
    0.49
     dinyatakan
    0.48
     ered
    0.47
     реаги
    0.47
    izuje
    0.47
     э
    0.46
     ଭ
    0.45
     appro
    0.45
     않는다
    0.45
     develops
    0.45
    POSITIVE LOGITS
    著
    0.49
    「
    0.46
    松
    0.46
    保护
    0.45
    介绍
    0.45
    甚
    0.44
    柔
    0.44
     colectivo
    0.43
    必
    0.43
    此刻
    0.41
    Activations Density 0.000%

    No Known Activations