© 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. 43942
    Prev
    Next
    INDEX
    Explanations

    legal citations "In re"

    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
    er
    -1.85
     où
    -1.66
     gdzie
    -1.60
    　↓
    -1.56
    Just
    -1.56
    工作人员
    -1.53
     где
    -1.49
     admired
    -1.49
     contribuer
    -1.48
    Quite
    -1.45
    POSITIVE LOGITS
    </strong>
    1.79
     a
    1.71
    祧
    1.55
    儅
    1.54
    {
    1.51
     شیپور
    1.50
    逦
    1.46
    mutlich
    1.46
     But
    1.45
     situate
    1.45
    Activations Density 0.052%

    No Known Activations