© 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. 123579
    Prev
    Next
    INDEX
    Explanations

    no denying that

    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
     to
    -1.75
     in
    -1.41
     tüm
    -1.39
     verme
    -1.38
    すぎて
    -1.38
     Erben
    -1.37
    >
    -1.36
    但在
    -1.35
    :
    -1.33
     ändå
    -1.32
    POSITIVE LOGITS
     that
    1.74
     einerseits
    1.65
     of
    1.65
    揩
    1.59
     lessen
    1.51
    媗
    1.50
    ING
    1.47
     preço
    1.44
    ة
    1.44
     phẩm
    1.42
    Activations Density 0.011%

    No Known Activations