© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 17674
    Prev
    Next
    INDEX
    Explanations

    Toki Pona word quantities

    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
     xmlns
    0.38
     প্রাচ
    0.37
    {})
    0.36
    Evaluating
    0.36
    ဿ
    0.34
    Density
    0.34
    Hosting
    0.34
    rophenyl
    0.34
    সিটি
    0.34
    Verification
    0.33
    POSITIVE LOGITS
     Mediator
    0.47
     Mediation
    0.42
     Meditation
    0.42
     ⚫
    0.40
     meditation
    0.39
     चुका
    0.39
     Mé
    0.38
    ياة
    0.37
     CHIKV
    0.37
     Меня
    0.37
    Activations Density 0.000%

    No Known Activations