© 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. 25846
    Prev
    Next
    INDEX
    Explanations

    it pronoun and its follow-ups

    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
     Puente
    -0.79
    liced
    -0.79
    yczą
    -0.77
    ANI
    -0.75
    СЯ
    -0.75
    ˝
    -0.75
    荃
    -0.74
    rentina
    -0.73
    брита
    -0.73
     quant
    -0.73
    POSITIVE LOGITS
     it
    1.84
    มัน
    1.34
    it
    1.05
     IT
    1.02
    它
    1.00
     esso
    0.97
    It
    0.96
     It
    0.90
     ello
    0.90
    ıt
    0.89
    Activations Density 0.050%

    No Known Activations