© 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. 104068
    Prev
    Next
    INDEX
    Explanations

    during, on, with

    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
    utiliz
    -1.53
    sugges
    -1.50
    が
    -1.33
     who
    -1.32
     flink
    -1.26
    recogn
    -1.24
     coinciden
    -1.24
    
    -1.23
    acknowled
    -1.23
     —
    -1.22
    POSITIVE LOGITS
     from
    2.47
     during
    2.44
     on
    2.14
     when
    1.91
     through
    1.90
     while
    1.81
     with
    1.66
     During
    1.62
     even
    1.56
     within
    1.52
    Activations Density 0.124%

    No Known Activations