© 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. 22-GEMMASCOPE-RES-131K
    7. 26774
    Prev
    Next
    INDEX
    Explanations

    epitopes or latent image area

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

    scientific text elements like research findings, technical specifications, and academic context.

    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_22/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
     gikk
    -1.01
     ngu
    -0.93
     trás
    -0.90
    ră
    -0.89
    sach
    -0.87
    賺
    -0.86
    鬧
    -0.85
    productList
    -0.85
    imageList
    -0.84
     verranno
    -0.83
    POSITIVE LOGITS
     börja
    1.03
     fréquemment
    1.03
     rompi
    0.93
     понадоби
    0.89
     hablaba
    0.87
    北欧
    0.86
    金币
    0.85
    Assay
    0.85
     Процитовано
    0.85
     honom
    0.84
    Activations Density 0.227%

    No Known Activations