© 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. 117684
    Prev
    Next
    INDEX
    Explanations

    drug, directions, or consult

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

    instructions or directions, particularly dosage information and administration guidelines.

    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
    そうに
    -0.84
    Basta
    -0.82
     abscess
    -0.81
     Syrie
    -0.81
    Вот
    -0.80
    先輩
    -0.78
     didik
    -0.78
     Tetapi
    -0.75
    бования
    -0.75
     VIA
    -0.74
    POSITIVE LOGITS
     consult
    1.25
    Consult
    1.07
     Consult
    1.04
     product
    1.00
    consult
    0.96
     children
    0.93
    product
    0.90
     intended
    0.87
    Directions
    0.87
     discontinue
    0.87
    Activations Density 0.012%

    No Known Activations