© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73938
    Prev
    Next
    INDEX
    Explanations

    referring to things or concepts

    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
     and
    -1.71
     then
    -1.70
     those
    -1.38
     another
    -1.34
     others
    -1.30
     adding
    -1.24
     additional
    -1.16
     so
    -1.16
     various
    -1.11
     regarding
    -1.10
    POSITIVE LOGITS
     it
    2.13
     its
    1.45
     It
    1.44
     มี
    1.30
    它
    1.27
     molto
    1.20
    它的
    1.20
    因为它
    1.17
     nó
    1.15
     оно
    1.13
    Activations Density 0.201%

    No Known Activations