© 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. 9650
    Prev
    Next
    INDEX
    Explanations

    words starting with Ele or asc

    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
    ing
    -2.88
    
    -2.75
    詎
    -2.73
    鷥
    -2.69
    猡
    -2.55
    勦
    -2.53
    sandalia
    -2.44
    喈
    -2.41
    ⢊
    -2.39
    笕
    -2.38
    POSITIVE LOGITS
    1
    4.59
    {
    3.25
    2
    3.08
    $
    2.84
    \
    2.73
    For
    2.61
    9
    2.48
     .
    2.47
    We
    2.42
     специалисты
    2.42
    Activations Density 0.007%

    No Known Activations