© 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. 31-GEMMASCOPE-2-RES-262K
    7. 18694
    Prev
    Next
    INDEX
    Explanations

    macro vs common name

    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
     van
    0.38
     Bath
    0.38
     суще
    0.38
     Cambridge
    0.38
     CSC
    0.37
     exced
    0.36
    Š
    0.36
     Communications
    0.36
     Совет
    0.36
     Combien
    0.35
    POSITIVE LOGITS
     disqualified
    0.41
    ้ม
    0.41
    λλην
    0.40
     unruly
    0.39
     orbiting
    0.38
     straighten
    0.38
     defiant
    0.38
    stung
    0.38
    taxonomy
    0.38
    籍
    0.38
    Activations Density 0.000%

    No Known Activations