© 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. 160167
    Prev
    Next
    INDEX
    Explanations

    followed by a preposition

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

    cost estimates

    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
    Фу
    0.50
    無
    0.49
    ५
    0.49
    ע
    0.48
    ನ್ನು
    0.47
    cdot
    0.46
    benzoimidazol
    0.46
    體
    0.45
     кана
    0.44
    悪
    0.44
    POSITIVE LOGITS
     दोषी
    0.47
     probleem
    0.47
    ्रेडिट
    0.45
     meriye
    0.44
     Bundle
    0.44
    觉得自己
    0.44
     DeV
    0.44
     Labor
    0.43
     January
    0.43
    觉得
    0.43
    Activations Density 0.001%

    No Known Activations