© 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. 10-GEMMASCOPE-RES-131K
    7. 85325
    Prev
    Next
    INDEX
    Explanations

    medication dosages or types

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

    numbers and combinations of digits in spam or prescription medication content.

    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
     Dinas
    -2.13
     whimsical
    -2.00
     astounding
    -1.93
    鷽
    -1.92
    閖
    -1.92
    擽
    -1.91
     quirky
    -1.84
     EIGHT
    -1.80
     quintessential
    -1.79
    蹰
    -1.78
    POSITIVE LOGITS
     two
    2.44
     three
    2.41
     Maybe
    2.33
     four
    2.30
     After
    2.20
     Really
    2.19
     eight
    2.14
     EVERY
    2.14
     get
    2.13
     one
    2.11
    Activations Density 0.005%

    No Known Activations