© 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. 119903
    Prev
    Next
    INDEX
    Explanations

    gmail addresses and names

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

    the name "Santini" or variations of proper names ending in similar letter patterns (like "Alli" and "gmail").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    焌
    -2.73
    嫫
    -2.66
    回想
    -2.66
    ):
    -2.59
    銛
    -2.48
    瀲
    -2.45
     asegur
    -2.45
    ༀ
    -2.41
     เห
    -2.34
     卧室
    -2.33
    POSITIVE LOGITS
     '
    2.66
     {
    2.64
    a
    2.53
    ’
    2.42
    [
    2.27
     нај
    2.25
     was
    2.16
    鹇
    2.13
                
    2.11
    いい
    2.09
    Activations Density 0.001%

    No Known Activations