© 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. 22334
    Prev
    Next
    INDEX
    Explanations

    surveyor, orbits, Delaunay, Q, Elenski

    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
     cheminée
    -1.96
     १
    -1.95
     или
    -1.91
     trésor
    -1.91
    }
    -1.90
     asamblea
    -1.81
     répondu
    -1.80
     véhicule
    -1.78
     Saltar
    -1.77
     Leitung
    -1.75
    POSITIVE LOGITS
    <td>
    1.89
    ↵
    1.85
     Their
    1.75
    D
    1.73
     männer
    1.71
    r
    1.66
     tma
    1.66
     between
    1.64
     paths
    1.64
    ,“
    1.63
    Activations Density 0.005%

    No Known Activations