© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22104
    Prev
    Next
    INDEX
    Explanations

    use

    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
    ❃
    -1.98
     sesi
    -1.91
    𓐍
    -1.82
     Entrega
    -1.80
     parfü
    -1.79
     betaling
    -1.78
    桄
    -1.77
    sterious
    -1.76
     uren
    -1.76
     they
    -1.74
    POSITIVE LOGITS
     ใช้
    2.05
    idjan
    1.87
     Use
    1.81
    8
    1.79
     характеристика
    1.74
                    
    1.72
     in
    1.70
     swój
    1.66
     said
    1.64
     Any
    1.63
    Activations Density 0.687%

    No Known Activations