© 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. 935
    Prev
    Next
    INDEX
    Explanations

    work on

    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
    3
    0.61
    การ
    0.59
    4
    0.58
    to
    0.57
    高
    0.54
    it
    0.54
    5
    0.53
    ו
    0.52
    大规模
    0.52
    ır
    0.51
    POSITIVE LOGITS
     Working
    0.68
    Working
    0.64
     Worked
    0.64
     pracuje
    0.64
     trabalhando
    0.62
     trabajar
    0.61
     Work
    0.60
    Worked
    0.60
     работают
    0.58
     lavorare
    0.58
    Activations Density 0.127%

    No Known Activations