© 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
    3. 40-GEMMASCOPE-2-RES-16K
    4. 11895
    Prev
    Next
    INDEX
    Explanations

    adhesive, glue, or fix

    np_acts-logits-general · gemini-2.5-flash-lite

    pasting, gluing, or adhering

    np_acts-logits-general · gemini-2.5-flash-lite

    adhesive

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shack
    0.47
    琲
    0.45
     ም
    0.42
     деревя
    0.41
    銑
    0.41
    籠
    0.40
     корпуса
    0.40
     handcuffed
    0.40
    Xml
    0.39
     tied
    0.39
    POSITIVE LOGITS
     adhesive
    2.00
     Adhesive
    1.93
    adhesive
    1.91
     adhesives
    1.80
    貼
    1.66
    贴
    1.65
    粘贴
    1.64
     adhes
    1.59
    貼り
    1.58
     glue
    1.51
    Activations Density 0.440%

    No Known Activations