© 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. 33408
    Prev
    Next
    INDEX
    Explanations

    Russian verbs describing state or 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
     없는
    -0.90
    ódó
    -0.89
     needing
    -0.80
     novelas
    -0.79
    endiendo
    -0.79
     гото
    -0.79
    ⚭
    -0.77
     правда
    -0.76
    appId
    -0.75
     believing
    -0.75
    POSITIVE LOGITS
     is
    1.41
     has
    0.94
     was
    0.84
     невели
    0.82
    不高
    0.78
     aktiviteter
    0.76
     shown
    0.75
     are
    0.75
     좋
    0.75
     done
    0.73
    Activations Density 0.020%

    No Known Activations