© 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. 82741
    Prev
    Next
    INDEX
    Explanations

    Russian word beginnings

    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
     now
    -0.97
     only
    -0.89
    ・・・」
    -0.80
     bär
    -0.80
    ابس
    -0.78
     syk
    -0.77
    举例
    -0.77
     gä
    -0.77
    などなど
    -0.77
    ！！」
    -0.75
    POSITIVE LOGITS
    nger
    0.86
    oteca
    0.85
    asana
    0.82
     siedz
    0.82
     premises
    0.80
    gef
    0.80
     undamaged
    0.79
     نوفمبر
    0.79
    咔嚓
    0.79
     افزایش
    0.78
    Activations Density 0.005%

    No Known Activations