© 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. 111180
    Prev
    Next
    INDEX
    Explanations

    logical implication $\implies$

    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
     politischen
    -1.63
    。　　
    -1.61
     漂亮
    -1.52
     可爱
    -1.49
    嘍
    -1.44
     또
    -1.41
    。】
    -1.41
     遇
    -1.40
     accustomed
    -1.38
     好看
    -1.38
    POSITIVE LOGITS
     opérés
    1.83
     }
    1.55
    S
    1.53
     définiti
    1.50
    jenige
    1.48
    c
    1.46
     leur
    1.45
    {
    1.45
     של
    1.42
    みたら
    1.41
    Activations Density 0.001%

    No Known Activations