© 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. 205750
    Prev
    Next
    INDEX
    Explanations

    utility function, floating rigs, helper, clandestine

    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
     contaminación
    0.50
     transmis
    0.45
     Federation
    0.44
    #__
    0.44
    nucleus
    0.43
     BBC
    0.42
     presidente
    0.42
     situação
    0.42
     feder
    0.41
    防控
    0.41
    POSITIVE LOGITS
     rivets
    0.44
    Worst
    0.40
    ่
    0.39
    omegran
    0.38
     remembered
    0.36
    用意
    0.36
     calma
    0.36
     decorative
    0.35
    保管
    0.35
     mids
    0.35
    Activations Density 0.001%

    No Known Activations