© 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. 84996
    Prev
    Next
    INDEX
    Explanations

    this and that demonstratives

    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
    鼉
    -1.77
     нашего
    -1.63
     μας
    -1.62
    鉏
    -1.61
    
    -1.59
    ⽼
    -1.59
     our
    -1.57
     (~(
    -1.55
    必要があります
    -1.55
     eenen
    -1.55
    POSITIVE LOGITS
     is
    2.59
     in
    2.38
     they
    2.34
     to
    2.31
     on
    2.25
     as
    2.22
     at
    2.19
     then
    2.13
     with
    2.09
     during
    2.09
    Activations Density 0.111%

    No Known Activations