© 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. 3864
    Prev
    Next
    INDEX
    Explanations

    conjunctions and prepositions

    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
    一种
    -1.00
     to
    -0.99
    гинал
    -0.95
     SUCH
    -0.94
    ското
    -0.93
     varje
    -0.93
     presets
    -0.91
    ͐
    -0.90
     WHOLE
    -0.90
    ateurs
    -0.90
    POSITIVE LOGITS
     it
    1.63
     this
    1.56
     everybody
    1.34
     everyone
    1.29
     then
    1.25
     when
    1.24
     their
    1.23
     its
    1.22
     Schicksal
    1.21
     various
    1.16
    Activations Density 0.379%

    No Known Activations