© 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. 10021
    Prev
    Next
    INDEX
    Explanations

    swirling vortex dissolving

    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
     monographs
    0.44
    gesetz
    0.43
     revisited
    0.43
     calculadora
    0.42
     monograph
    0.42
     sobres
    0.42
    骗
    0.42
     preoccupation
    0.41
     eszköz
    0.41
    騙
    0.41
    POSITIVE LOGITS
     billowing
    0.64
     vortex
    0.63
     flames
    0.63
     beams
    0.63
     fissures
    0.63
     walls
    0.63
     teleport
    0.62
     aura
    0.62
     shimmering
    0.61
     beam
    0.59
    Activations Density 0.036%

    No Known Activations