© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91491
    Prev
    Next
    INDEX
    Explanations

    Russian prefixes "от", "ото"

    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
    <bos>
    -0.93
    <0xA3>
    -0.92
     also
    -0.81
    チャンス
    -0.79
    内容は
    -0.79
    ⽅
    -0.78
    結果は
    -0.78
    などを
    -0.77
    先は
    -0.77
    道を
    -0.76
    POSITIVE LOGITS
     איז
    0.93
    Allocate
    0.90
    Adventure
    0.90
     parfaite
    0.89
    От
    0.89
    mit
    0.88
     gebeten
    0.88
    rescence
    0.87
     hipote
    0.87
    ρων
    0.87
    Activations Density 0.002%

    No Known Activations