© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66482
    Prev
    Next
    INDEX
    Explanations

    family and health

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

    references to "family" in the context of products, services, or health concerns.

    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
    there
    -1.66
     kehadiran
    -1.52
    wandel
    -1.46
     arrend
    -1.35
    きちんと
    -1.34
     bencana
    -1.33
     there
    -1.33
     Japón
    -1.30
     gelar
    -1.29
     Canadá
    -1.28
    POSITIVE LOGITS
     &
    1.58
     this
    1.55
    向了
    1.45
     Again
    1.37
     \&
    1.34
    ⩖
    1.33
     today
    1.33
    },
    1.31
     who
    1.31
     για
    1.30
    Activations Density 0.018%

    No Known Activations