© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40792
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    2
    -2.59
    4
    -2.52
    0
    -2.48
    5
    -2.39
     It
    -2.38
    9
    -2.36
    7
    -2.20
     Instead
    -2.17
     Should
    -2.13
    8
    -2.11
    POSITIVE LOGITS
     土産
    2.06
    ⃢
    1.97
     contoh
    1.92
    螄
    1.92
     ſame
    1.90
    haften
    1.88
    嗵
    1.87
    璆
    1.83
     økonom
    1.80
    　　（
    1.78
    Activations Density 0.009%

    No Known Activations