© 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. 131377
    Prev
    Next
    INDEX
    Explanations

    parts of descriptions and definitions

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

    asking what describes

    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
     dataset
    0.57
     %.
    0.53
     %),
    0.50
     UIKit
    0.49
     svc
    0.49
     datasets
    0.48
     reminds
    0.47
     dispenser
    0.47
     %).
    0.47
     bystand
    0.46
    POSITIVE LOGITS
    ת
    0.51
     verdadero
    0.50
     המו
    0.49
    Erro
    0.48
    하겠습니다
    0.48
    ędzie
    0.48
    ОВА
    0.47
    ОВ
    0.47
    වීම
    0.47
    сти
    0.46
    Activations Density 0.000%

    No Known Activations