© 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. 22-GEMMASCOPE-RES-131K
    7. 34231
    Prev
    Next
    INDEX
    Explanations

    ObjectMapper

    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_22/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
     souver
    -0.85
     diametro
    -0.83
     sosi
    -0.81
    Abs
    -0.81
     usual
    -0.80
     decides
    -0.78
    代码
    -0.77
     coloris
    -0.77
    Added
    -0.77
     lipat
    -0.77
    POSITIVE LOGITS
     tantos
    1.14
     tantas
    0.99
    ář
    0.90
    NavLink
    0.90
    ECI
    0.88
     kissing
    0.87
    Française
    0.85
    harvard
    0.85
     handcu
    0.85
    талия
    0.85
    Activations Density 0.173%

    No Known Activations