© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92293
    Prev
    Next
    INDEX
    Explanations

    verbs followed by it

    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_34/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
     них
    -1.98
     których
    -1.83
     nepiecieš
    -1.74
     viņ
    -1.73
    iters
    -1.63
     izman
    -1.60
     которыми
    -1.56
     которых
    -1.53
    )}$.
    -1.51
     kecuali
    -1.49
    POSITIVE LOGITS
     it
    15.38
    它
    5.81
     It
    5.31
     оно
    4.56
    มัน
    4.41
     มัน
    4.34
     它
    4.31
    It
    3.78
    它是
    3.69
    把它
    3.63
    Activations Density 2.654%

    No Known Activations