© 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. 34-GEMMASCOPE-RES-131K
    7. 2593
    Prev
    Next
    INDEX
    Explanations

    texas court of appeals

    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_34/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
     doll
    -0.82
    olito
    -0.75
     nepri
    -0.75
     Мой
    -0.72
     Providing
    -0.71
     lặng
    -0.70
    
    -0.69
    āli
    -0.69
     ferru
    -0.69
    doll
    -0.68
    POSITIVE LOGITS
     party
    0.85
    Expr
    0.80
    Party
    0.78
    муля
    0.76
    wicklung
    0.76
    TEXAS
    0.76
     Party
    0.75
     MacMillan
    0.75
    ainville
    0.74
     cytometry
    0.72
    Activations Density 0.002%

    No Known Activations