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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84814
    Prev
    Next
    INDEX
    Explanations

    family members and relationships

    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
     it
    -2.09
     or
    -1.73
     about
    -1.52
     spotkania
    -1.43
     then
    -1.33
     hábiles
    -1.33
     horaire
    -1.22
     Context
    -1.21
     cómoda
    -1.21
     documents
    -1.20
    POSITIVE LOGITS
    很喜欢
    1.62
    Бил
    1.44
     aidant
    1.41
    今年も
    1.41
     musées
    1.40
     policiers
    1.38
    ’
    1.37
     enlar
    1.35
    ultimo
    1.34
    蜮
    1.32
    Activations Density 0.001%

    No Known Activations