© 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. 123810
    Prev
    Next
    INDEX
    Explanations

    bad quality or situation

    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
    :][
    -1.63
    ACIÓN
    -1.50
     —
    -1.48
     kabát
    -1.46
    ERTO
    -1.45
    chiato
    -1.44
    UALA
    -1.42
    桄
    -1.41
    戩
    -1.41
    UCION
    -1.41
    POSITIVE LOGITS
    s
    1.84
    )
    1.50
     commande
    1.41
    遢
    1.35
     può
    1.34
     next
    1.32
     seulement
    1.29
    Only
    1.28
    另一個
    1.27
     clic
    1.26
    Activations Density 0.010%

    No Known Activations