© 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. 22216
    Prev
    Next
    INDEX
    Explanations

    `AssemblyCompany`, `Q:`, `Current treatment`, `Please tell`

    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
     my
    -1.94
    );
    -1.85
     Our
    -1.81
     engaging
    -1.77
    ться
    -1.76
     tetapi
    -1.76
    .,
    -1.75
     Would
    -1.70
     or
    -1.62
     offer
    -1.62
    POSITIVE LOGITS
    InjectAttribute
    2.25
    鹮
    2.00
    
    1.97
     rocha
    1.95
     that
    1.84
     massac
    1.82
     renunci
    1.81
    橚
    1.80
     they
    1.80
    웻
    1.75
    Activations Density 0.000%

    No Known Activations