© 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. 3728
    Prev
    Next
    INDEX
    Explanations

    is/are/do/provide/request/change/predict

    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
     ಮಾಡಲು
    0.61
     yelled
    0.56
    的時候
    0.55
    uradaki
    0.54
     sempat
    0.54
     merasakan
    0.53
    靂
    0.53
     Pogis
    0.52
     flashed
    0.52
     excitedly
    0.52
    POSITIVE LOGITS
    입니다
    0.77
    이다
    0.70
     것이다
    0.66
    であり
    0.64
    이며
    0.64
     것입니다
    0.60
    으며
    0.60
    ).
    0.59
    다
    0.57
     있습니다
    0.55
    Activations Density 0.009%

    No Known Activations