© 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. 47812
    Prev
    Next
    INDEX
    Explanations

    introducing the first item

    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
     also
    -1.84
     other
    -1.78
    {
    -1.35
     others
    -1.30
    sequently
    -1.24
    Também
    -1.23
     further
    -1.20
    ubscribe
    -1.18
     myös
    -1.16
     عربي
    -1.16
    POSITIVE LOGITS
    któ
    1.47
     moks
    1.31
    ARING
    1.27
     menyenangkan
    1.27
     obro
    1.23
     about
    1.16
     soupe
    1.15
     Agricultura
    1.13
    leicht
    1.13
    FORMANCE
    1.13
    Activations Density 0.091%

    No Known Activations