© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104821
    Prev
    Next
    INDEX
    Explanations

    insertion context

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

    the word "insertion" in technical and medical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     месе
    -2.27
    ússia
    -2.27
     رائعة
    -2.23
     مختلفة
    -2.17
    实的
    -2.16
     広場
    -2.16
    观的
    -2.11
     bruge
    -2.09
    and
    -2.09
     vulgaires
    -2.05
    POSITIVE LOGITS
            
    2.77
     When
    2.52
    h
    2.42
     singularly
    2.33
    </i>
    2.33
    他们的
    2.31
               
    2.22
    ְׁ
    2.22
    "
    2.19
     quando
    2.17
    Activations Density 0.009%

    No Known Activations