© 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. 13274
    Prev
    Next
    INDEX
    Explanations

    types ofaction-oriented

    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
     lessened
    0.62
    での
    0.58
     lessening
    0.54
    有着
    0.52
    想着
    0.51
    盻
    0.49
     needing
    0.48
     значений
    0.47
    듦
    0.46
    此
    0.45
    POSITIVE LOGITS
     Darüber
    0.49
     Nevertheless
    0.48
     Međutim
    0.47
     deshalb
    0.47
     Deshalb
    0.46
     Meskipun
    0.45
    itherto
    0.44
     miraculously
    0.44
    ischer
    0.43
    よりも
    0.42
    Activations Density 0.007%

    No Known Activations