© 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. 60082
    Prev
    Next
    INDEX
    Explanations

    location particles

    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
    で使
    -1.17
    で使用
    -1.09
     pestaña
    -1.02
    へ向
    -0.97
    へ行
    -0.96
     jusqu
    -0.95
    で見る
    -0.88
    にします
    -0.87
    で購入
    -0.86
     combinación
    -0.85
    POSITIVE LOGITS
    에
    3.22
    に
    3.09
    には
    2.59
    에는
    2.41
    にも
    2.09
     に
    1.98
    りに
    1.86
     to
    1.83
    일에
    1.56
    에도
    1.51
    Activations Density 0.012%

    No Known Activations