© 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. 129112
    Prev
    Next
    INDEX
    Explanations

    human tissue physical indications

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

    phrases related to absence or lacking something, particularly in technical or formal contexts.

    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
    録画
    -0.81
     combined
    -0.79
       
    -0.77
     wszystkim
    -0.76
     
    -0.75
    涉及
    -0.72
    同学们
    -0.72
     slogan
    -0.71
     vanwege
    -0.71
    でもある
    -0.70
    POSITIVE LOGITS
    鹩
    1.04
    dür
    1.02
     UITableView
    0.96
     konkret
    0.95
     praktis
    0.94
     spesifik
    0.92
     bensin
    0.90
    viewDidLoad
    0.90
     rajut
    0.90
     teknis
    0.89
    Activations Density 0.164%

    No Known Activations