© 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. 63387
    Prev
    Next
    INDEX
    Explanations

    obesity, obese, inflammation, and signaling cause complications

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

    text discussing medical and health conditions, particularly obesity and disease.

    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_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
    詔
    -0.91
    бити
    -0.82
    helps
    -0.82
     empowering
    -0.81
    helped
    -0.81
     गए
    -0.81
    μφ
    -0.81
    갓
    -0.80
    ἔ
    -0.80
     dient
    -0.80
    POSITIVE LOGITS
     contribute
    2.22
     contributes
    1.87
     contributing
    1.76
     linked
    1.68
     contributor
    1.64
     contributed
    1.64
     contribution
    1.64
     predis
    1.63
     contributors
    1.56
     Contribute
    1.43
    Activations Density 0.291%

    No Known Activations