© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67245
    Prev
    Next
    INDEX
    Explanations

    Amy followed by names or medical terms

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

    the name "Amy" within text, with particularly high activation for medical terms like "amyloidosis" when it follows.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    銠
    -2.56
    
    -2.36
    曁
    -2.25
    匍
    -2.19
    多彩
    -2.17
    利益
    -2.16
     cambi
    -2.14
     amount
    -2.14
    .”.
    -2.14
    必定
    -2.09
    POSITIVE LOGITS
    </td>
    2.67
    线的
    2.55
    [
    2.36
    颪
    2.34
                        
    2.27
         
    2.23
    了吗
    2.22
    ↵↵
    2.20
    なんだけど
    2.19
    ቧ
    2.19
    Activations Density 0.008%

    No Known Activations