© 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. 10-GEMMASCOPE-RES-131K
    7. 41845
    Prev
    Next
    INDEX
    Explanations

    Russian words and fstream

    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_10/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
     alamu
    -2.73
     faſt
    -2.63
    üşonlu
    -2.59
    锖
    -2.58
    皷
    -2.53
     historische
    -2.47
    ೣ
    -2.45
    昪
    -2.44
    Loves
    -2.44
     gustaMe
    -2.36
    POSITIVE LOGITS
    >
    3.31
     Whether
    3.30
     After
    3.05
     It
    2.95
    after
    2.86
    {
    2.86
    I
    2.81
     Because
    2.81
     With
    2.77
     There
    2.70
    Activations Density 0.001%

    No Known Activations