© 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. 113825
    Prev
    Next
    INDEX
    Explanations

    properties and computed selectors

    np_acts-logits-general · gemini-2.5-flash-lite

    the `@property` decorator or keyword in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    谕
    -1.70
     competición
    -1.67
    我们在
    -1.63
    我们将
    -1.59
    ;}
    
    -1.57
     advertencia
    -1.57
    言えば
    -1.55
     mehrere
    -1.52
     and
    -1.49
    hasia
    -1.47
    POSITIVE LOGITS
    '
    1.93
     farbe
    1.87
     weichen
    1.72
     they
    1.69
    The
    1.63
     wußte
    1.59
     erz
    1.59
    黝
    1.59
     schuhe
    1.59
    寕
    1.58
    Activations Density 0.002%

    No Known Activations