© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 228136
    Prev
    Next
    INDEX
    Explanations

    exchange, way to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    都會
    0.52
     consulting
    0.49
     výsled
    0.49
     relatório
    0.48
     gerenci
    0.48
     consulté
    0.48
     certific
    0.47
    霆
    0.47
     maioria
    0.46
     modernisation
    0.46
    POSITIVE LOGITS
    icots
    0.56
    ade
    0.47
     شیع
    0.47
    atrice
    0.45
    uncture
    0.44
    uest
    0.43
    asia
    0.43
    atile
    0.42
    iere
    0.42
     किंग्स
    0.42
    Activations Density 0.000%

    No Known Activations