© 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-262K
    7. 84617
    Prev
    Next
    INDEX
    Explanations

    classification and partitioning

    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_262k_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
     fii
    0.45
     loop
    0.44
     industri
    0.43
     Wi
    0.43
     g
    0.42
     sm
    0.41
     JDBC
    0.41
    霭
    0.41
    퐫
    0.41
     ui
    0.40
    POSITIVE LOGITS
     قبل
    0.51
    距离
    0.51
    ОВА
    0.51
    أ
    0.51
    ية
    0.50
     Reactors
    0.50
    مة
    0.50
    Ку
    0.50
    این
    0.49
    attled
    0.49
    Activations Density 0.001%

    No Known Activations