© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30696
    Prev
    Next
    INDEX
    Explanations

    Russian words and names

    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
     several
    -0.79
     modify
    -0.75
     kock
    -0.74
    Ngh
    -0.73
    واه
    -0.72
     related
    -0.70
     textil
    -0.70
     three
    -0.70
     Modif
    -0.68
     sirup
    -0.68
    POSITIVE LOGITS
    INVEST
    0.84
     jego
    0.83
    vrigt
    0.80
    そちら
    0.79
    wens
    0.77
     рай
    0.76
     soi
    0.75
    trans
    0.75
     Ausnahme
    0.74
    setLong
    0.74
    Activations Density 0.023%

    No Known Activations