© 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. 29522
    Prev
    Next
    INDEX
    Explanations

    illegal annexation

    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
    typicode
    0.52
     Metabolic
    0.46
    ícul
    0.45
     یقینی
    0.45
     Subsec
    0.42
     налого
    0.41
     metabolic
    0.40
    韪
    0.40
    渍
    0.40
    มาะ
    0.40
    POSITIVE LOGITS
     business
    0.39
     frog
    0.39
     Business
    0.39
    const
    0.38
     Frog
    0.38
     thin
    0.38
     const
    0.38
     bending
    0.37
     Gartner
    0.36
     population
    0.36
    Activations Density 0.000%

    No Known Activations