© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39773
    Prev
    Next
    INDEX
    Explanations

    coming together or resolving

    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
     then
    -1.98
     by
    -1.82
     if
    -1.63
     it
    -1.51
     here
    -1.34
     is
    -1.31
    ↵↵
    -1.30
     who
    -1.30
     findest
    -1.23
     when
    -1.22
    POSITIVE LOGITS
     všetko
    1.37
     omkring
    1.34
     akci
    1.32
     različ
    1.29
     faktiskt
    1.28
    娲
    1.27
     jednod
    1.26
     éton
    1.26
     aldrig
    1.23
    zeichnete
    1.22
    Activations Density 0.041%

    No Known Activations