© 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. 20621
    Prev
    Next
    INDEX
    Explanations

    upcoming changes or recent interactions

    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
    Forever
    0.47
    onen
    0.45
     визуа
    0.45
    ließlich
    0.45
    mond
    0.44
     Forever
    0.44
     だ
    0.43
    विंद
    0.43
    विज्ञान
    0.43
     reimag
    0.42
    POSITIVE LOGITS
    ي
    0.52
     Chamb
    0.44
     Campe
    0.43
     Kwiatkowski
    0.42
    ப்பது
    0.40
    י
    0.39
     unites
    0.39
     pests
    0.39
     Campeonato
    0.39
     offices
    0.38
    Activations Density 0.001%

    No Known Activations