© 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. 40773
    Prev
    Next
    INDEX
    Explanations

    structure, headers, lists

    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
    dens
    0.46
    䧺
    0.46
     የወ
    0.44
    ៤
    0.44
    ერის
    0.43
    وزيع
    0.43
     húmed
    0.43
    liği
    0.42
    韫
    0.42
    മി
    0.41
    POSITIVE LOGITS
    。
    0.43
     default
    0.43
    <!
    0.38
     template
    0.38
     Default
    0.38
     때문
    0.38
     users
    0.38
    ।
    0.38
    Default
    0.37
     uninstall
    0.35
    Activations Density 0.013%

    No Known Activations