© 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. 99171
    Prev
    Next
    INDEX
    Explanations

    legal opinions and court documents

    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
    俢
    -2.17
    ⃢
    -1.97
     diminuer
    -1.91
    ulence
    -1.87
    jeuner
    -1.82
    Zug
    -1.80
    彀
    -1.80
    腠
    -1.80
     durer
    -1.74
     málo
    -1.74
    POSITIVE LOGITS
    出了一
    2.23
     at
    1.99
    There
    1.96
     in
    1.95
     has
    1.81
     At
    1.80
     will
    1.79
    ).
    1.74
    颯
    1.71
    At
    1.70
    Activations Density 0.004%

    No Known Activations