© 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. 16-GEMMASCOPE-2-RES-65K
    7. 513
    Prev
    Next
    INDEX
    Explanations

    major expansion

    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_16_width_65k_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
     proteína
    0.48
    et
    0.45
    p
    0.41
     mág
    0.39
    on
    0.38
    y
    0.38
     ciências
    0.38
     manej
    0.38
     már
    0.37
     cualquier
    0.37
    POSITIVE LOGITS
     in
    0.49
     an
    0.37
     and
    0.36
     initiated
    0.34
     epitome
    0.34
    들이
    0.34
    도
    0.33
     accused
    0.32
     awareness
    0.32
    지
    0.32
    Activations Density 0.000%

    No Known Activations