© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115860
    Prev
    Next
    INDEX
    Explanations

    tasks needing resolution

    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
     agarre
    -1.06
    unakan
    -1.01
    Siapa
    -1.00
    Manfaat
    -1.00
     umożli
    -0.98
     mög
    -0.96
    Used
    -0.95
     sienta
    -0.94
    参考にして
    -0.92
    Lá
    -0.91
    POSITIVE LOGITS
     to
    4.47
     that
    3.16
    需要
    2.48
     needing
    2.47
     cần
    2.31
     need
    1.88
    ที่จะ
    1.78
    ต้อง
    1.77
     需要
    1.76
     needs
    1.66
    Activations Density 0.074%

    No Known Activations