© 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-262K
    7. 110116
    Prev
    Next
    INDEX
    Explanations

    peaceful nuclear energy and safeguards

    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_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
     concaten
    0.52
    电话
    0.51
     neuropsych
    0.51
     circula
    0.50
     ﺍﻟ
    0.50
    휼
    0.50
    ﻈ
    0.49
     concatenate
    0.48
     públicas
    0.48
     ημέ
    0.48
    POSITIVE LOGITS
     IAEA
    0.62
     Atomic
    0.55
     Similarly
    0.52
     Ä
    0.51
     Vatican
    0.51
     Security
    0.49
     Facilities
    0.49
     Anti
    0.48
     Likewise
    0.48
     Atom
    0.48
    Activations Density 0.002%

    No Known Activations