© 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. 104297
    Prev
    Next
    INDEX
    Explanations

    He/She followed by a verb

    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
     or
    -1.45
     which
    -1.18
     Berufung
    -1.09
     then
    -1.09
    giaan
    -1.09
    buzo
    -1.09
     Américas
    -1.08
     peraturan
    -1.07
     Vereinig
    -1.06
     &=&
    -1.06
    POSITIVE LOGITS
     [
    1.63
     really
    1.51
     we
    1.27
     
    1.27
     kind
    1.26
     tremendous
    1.26
     I
    1.25
    '
    1.24
     очень
    1.21
     didn
    1.20
    Activations Density 0.010%

    No Known Activations