© 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. 63141
    Prev
    Next
    INDEX
    Explanations

    ECU, controller, vehicle, coding

    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
    zano
    -0.83
    λαμβ
    -0.81
    ABSTRACT
    -0.77
    emp
    -0.73
     Rioja
    -0.72
     sinn
    -0.71
    競馬
    -0.71
    uum
    -0.71
    yns
    -0.71
    aders
    -0.70
    POSITIVE LOGITS
    Coding
    0.96
    uchte
    0.87
    AHL
    0.82
     Coding
    0.80
    ₖ
    0.80
     coding
    0.79
     psz
    0.79
     Module
    0.78
     module
    0.77
     gateways
    0.76
    Activations Density 0.007%

    No Known Activations