© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9338
    Prev
    Next
    INDEX
    Explanations

    conditions met or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     справедливо
    0.41
    తున్నారు
    0.39
    łeś
    0.39
    ftest
    0.39
    为什么
    0.38
    ాం
    0.38
     многим
    0.38
    셨
    0.37
    效应
    0.37
     provavelmente
    0.37
    POSITIVE LOGITS
     veya
    0.51
     কিংবা
    0.50
     whatsoever
    0.49
     eenvoudig
    0.48
     alebo
    0.47
     ή
    0.46
    하거나
    0.46
     ಅಥವಾ
    0.45
     или
    0.44
     अथवा
    0.44
    Activations Density 0.124%

    No Known Activations