© 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-16K
    7. 1316
    Prev
    Next
    INDEX
    Explanations

    table values

    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_16k_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
    ㅋㅋㅋㅋㅋㅋㅋㅋ
    0.59
                                   
    0.57
    ដែលមាន
    0.50
    についても
    0.50
    ----------------
    0.49
    ட்டிக்க
    0.49
     menyebabkan
    0.47
     seventeen
    0.47
     troisième
    0.47
     ebenfalls
    0.46
    POSITIVE LOGITS
     socalled
    0.75
     അദ്ദേ
    0.61
     wellknown
    0.57
    混凝
    0.55
     longterm
    0.52
     utili
    0.52
     $%
    0.51
     США
    0.51
     elec
    0.49
    ďaka
    0.48
    Activations Density 0.400%

    No Known Activations