© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28731
    Prev
    Next
    INDEX
    Explanations

    z-code diseases

    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
    مه
    0.56
    ка
    0.50
     دي
    0.49
    經過
    0.49
    شه
    0.48
    ك
    0.48
    紀
    0.48
    聲
    0.47
    Chi
    0.46
    functie
    0.46
    POSITIVE LOGITS
     oat
    0.51
     Bred
    0.49
     whenever
    0.48
    ossen
    0.46
     foams
    0.46
     when
    0.45
    ockeys
    0.44
     outputs
    0.44
     for
    0.44
     J
    0.44
    Activations Density 0.000%

    No Known Activations