© 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. 98231
    Prev
    Next
    INDEX
    Explanations

    probability and likelihood

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on Cyrillic (Russian) text segments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    zensionen
    -0.83
    pump
    -0.82
    passen
    -0.80
     方法
    -0.79
     diferenças
    -0.78
    ----</
    -0.76
    fällt
    -0.76
    řen
    -0.75
    ürgen
    -0.75
    Comparison
    -0.75
    POSITIVE LOGITS
     probability
    6.13
     probabilities
    5.22
    probability
    4.50
    Probability
    4.47
     Probability
    4.44
    概率
    3.98
     вероят
    3.70
     probab
    3.58
     Probab
    3.48
     likelihood
    3.47
    Activations Density 0.113%

    No Known Activations