© 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. 60465
    Prev
    Next
    INDEX
    Explanations

    ISO country and language codes

    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
     freundlichen
    -0.74
     obviously
    -0.71
     colorida
    -0.71
     Ngày
    -0.71
     sindaco
    -0.71
     duyên
    -0.71
     examined
    -0.67
     paragraph
    -0.67
     attuale
    -0.65
     Siamese
    -0.65
    POSITIVE LOGITS
     ISO
    2.97
    ISO
    2.50
     iso
    2.13
     Iso
    1.89
    iso
    1.88
    Iso
    1.88
     codes
    1.65
     code
    1.59
    Codes
    1.46
     код
    1.39
    Activations Density 0.050%

    No Known Activations