© 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. 75386
    Prev
    Next
    INDEX
    Explanations

    book flights, compute environments, pain severity

    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
     réaliser
    0.54
     Möglich
    0.50
     erect
    0.48
     envis
    0.47
    䇞
    0.47
     pilgr
    0.47
     realizzazione
    0.46
     opposites
    0.46
     sû
    0.46
     inev
    0.45
    POSITIVE LOGITS
    ГА
    0.50
    Ц
    0.45
    Advanced
    0.44
    *
    0.44
    ч
    0.44
    की
    0.44
    кой
    0.43
    Fish
    0.43
    Хар
    0.43
    둥
    0.43
    Activations Density 0.001%

    No Known Activations