© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 518
    Prev
    Next
    INDEX
    Explanations

    Helen followed by a name

    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
     unterschied
    -2.44
    u
    -2.41
     yüzden
    -2.39
    จะเป็น
    -2.38
     その
    -2.38
     In
    -2.38
    留意
    -2.28
    迳
    -2.28
     него
    -2.20
    ⢕
    -2.20
    POSITIVE LOGITS
    {
    2.84
     Juillet
    2.61
    ate
    2.55
    ”(
    2.55
     wth
    2.50
    The
    2.48
    ation
    2.47
    媖
    2.47
     piti
    2.45
     kerana
    2.45
    Activations Density 0.004%

    No Known Activations