© 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. 34-GEMMASCOPE-RES-131K
    7. 117338
    Prev
    Next
    INDEX
    Explanations

    family friendly or associated services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    私には
    -0.86
    給你
    -0.85
    嬰兒
    -0.83
    fycat
    -0.81
     Zelle
    -0.79
    カップル
    -0.78
     soggetto
    -0.77
     संप
    -0.77
    目錄
    -0.77
    贅沢
    -0.76
    POSITIVE LOGITS
     friendly
    1.61
    friendly
    1.42
     Friendly
    1.39
    Friendly
    1.38
     fun
    1.24
     Fun
    1.16
    👨
    1.13
    Fun
    1.10
     oriented
    1.04
     affair
    1.01
    Activations Density 0.016%

    No Known Activations