© 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. 12392
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by pronouns

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

    for you

    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
    S
    0.46
    M
    0.46
    L
    0.41
    E
    0.41
    B
    0.40
     sechs
    0.40
    G
    0.40
    O
    0.39
    istered
    0.39
     পাঁচটি
    0.39
    POSITIVE LOGITS
     mình
    0.52
     sobą
    0.49
     siebie
    0.47
     him
    0.47
     niego
    0.47
     us
    0.46
    ตัวเอง
    0.41
    你了
    0.40
     nhau
    0.40
     něj
    0.39
    Activations Density 0.162%

    No Known Activations