© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12655
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ව්
    0.70
    usstsein
    0.67
    ̍
    0.64
    ὸς
    0.63
     murderous
    0.60
    othelial
    0.59
     Gandh
    0.59
    mselves
    0.59
     Waals
    0.59
     fanciful
    0.59
    POSITIVE LOGITS
     [
    3.02
     ____
    3.00
     ________
    2.95
     _______
    2.95
     _____
    2.90
     ______
    2.87
     ____________
    2.85
     __________
    2.80
     ___
    2.62
    ____
    2.54
    Activations Density 0.445%

    No Known Activations