© 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. 113474
    Prev
    Next
    INDEX
    Explanations

    taken to

    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
    '
    -1.86
          
    -1.63
     not
    -1.63
     comes
    -1.32
     dejó
    -1.31
    🢒
    -1.30
    除此之外
    -1.30
    コメ
    -1.28
     terminó
    -1.25
     perdió
    -1.25
    POSITIVE LOGITS
     to
    2.06
    1.46
    Then
    1.42
    inverno
    1.38
    évaluation
    1.30
    Would
    1.27
     />';
    1.27
    1.27
    1.27
    摀
    1.26
    Activations Density 0.041%

    No Known Activations