© 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. 22-GEMMASCOPE-RES-131K
    7. 104605
    Prev
    Next
    INDEX
    Explanations

    `data-` attributes and `utm` parameters

    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_22/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
     sirop
    -1.41
     Kristus
    -1.38
     türkiye
    -1.34
     akum
    -1.34
     romantis
    -1.31
     instala
    -1.29
     Sté
    -1.28
     atlet
    -1.27
     hakim
    -1.26
     persil
    -1.25
    POSITIVE LOGITS
    For
    1.46
    He
    1.41
    To
    1.38
    With
    1.35
     also
    1.32
    O
    1.30
    This
    1.28
    L
    1.27
    We
    1.25
    By
    1.21
    Activations Density 0.004%

    No Known Activations