© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79597
    Prev
    Next
    INDEX
    Explanations

    scaling, savings, prevent future, benchmarking

    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
    ha
    0.45
    се
    0.44
     উচিত
    0.44
    pl
    0.44
    霭
    0.43
    ch
    0.42
    зан
    0.42
    remember
    0.41
     বিজ্ঞান
    0.41
    ли
    0.40
    POSITIVE LOGITS
     ນ
    0.51
     goreng
    0.50
     marinas
    0.49
     armazenamento
    0.49
     toxicants
    0.48
     kinase
    0.48
     dugo
    0.47
     "?
    0.46
     Championships
    0.44
     gamepad
    0.43
    Activations Density 0.005%

    No Known Activations