© 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. 101955
    Prev
    Next
    INDEX
    Explanations

    descriptive words preceding nouns

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

    precise geometry, appointment scheduling

    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
    σης
    0.50
    ющей
    0.46
     სხვა
    0.46
    các
    0.45
    верса
    0.44
    ᱽ
    0.44
     효과
    0.43
    သူ
    0.43
    传播
    0.42
    ющая
    0.42
    POSITIVE LOGITS
     trif
    0.49
    anden
    0.47
    ُونَ
    0.46
     latitudine
    0.46
     sann
    0.44
    alte
    0.44
    ande
    0.43
     cooking
    0.43
    andi
    0.43
     mesti
    0.42
    Activations Density 0.000%

    No Known Activations