© 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. 91576
    Prev
    Next
    INDEX
    Explanations

    Russian word "вы" followed by verbs of action

    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
     out
    -0.82
    onic
    -0.75
     nel
    -0.73
     in
    -0.73
    IV
    -0.71
    ardo
    -0.71
     impairment
    -0.71
    J
    -0.69
    langle
    -0.69
     Emirates
    -0.69
    POSITIVE LOGITS
    OURS
    0.91
    為に
    0.88
     oorspron
    0.86
     tessuto
    0.85
    érable
    0.85
     unicórnio
    0.84
    選ば
    0.83
    ₈
    0.82
    ;*
    0.82
     ungew
    0.81
    Activations Density 0.003%

    No Known Activations