© 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. 34-GEMMASCOPE-RES-131K
    7. 117050
    Prev
    Next
    INDEX
    Explanations

    directions, dosage, ingredients

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

    product labels and specifications in health/supplement descriptions.

    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
    aktionen
    -1.00
     Meksi
    -0.96
    ceptable
    -0.89
     Sosial
    -0.88
     portail
    -0.84
     vœux
    -0.84
     verschiedener
    -0.84
    мость
    -0.83
    ferent
    -0.83
    近年
    -0.82
    POSITIVE LOGITS
     directions
    1.82
     Directions
    1.68
     instructions
    1.62
     storage
    1.60
    Directions
    1.55
     usage
    1.49
     ingredients
    1.48
    directions
    1.47
     dosage
    1.45
     recommended
    1.45
    Activations Density 0.021%

    No Known Activations