© 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. 14933
    Prev
    Next
    INDEX
    Explanations

    help and information

    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
    '
    -2.63
     kurzem
    -1.71
     і
    -1.63
     stratég
    -1.59
    ｺ
    -1.57
     feitas
    -1.56
    　　（
    -1.53
    ↵
    -1.52
     feitos
    -1.46
     Significance
    -1.45
    POSITIVE LOGITS
    {
    2.03
    7
    2.02
    或者
    1.95
    help
    1.79
     meravigli
    1.72
     Help
    1.71
    纔
    1.70
    ⟝
    1.70
    ].
    1.69
    也很
    1.69
    Activations Density 0.042%

    No Known Activations