© 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. 40-GEMMASCOPE-2-RES-262K
    7. 120532
    Prev
    Next
    INDEX
    Explanations

    common words

    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_40_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
    aye
    0.41
     Vary
    0.41
    )):
    0.40
    Airplane
    0.40
     Tbilisi
    0.39
    JUL
    0.38
    ")):
    0.38
    Aye
    0.38
    Jan
    0.38
    Xem
    0.37
    POSITIVE LOGITS
     común
    0.46
     ඉතා
    0.43
    grasp
    0.42
    }\!\
    0.42
     coaster
    0.41
     comum
    0.41
     comunes
    0.41
    獧
    0.40
    कांक्षा
    0.38
    籤
    0.38
    Activations Density 0.001%

    No Known Activations