© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93310
    Prev
    Next
    INDEX
    Explanations

    staying safe and healthy

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

    content related to COVID-19 prevention measures and public health guidance.

    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_22/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
     åren
    -1.30
     selepas
    -1.24
     brukar
    -1.13
    接続
    -1.09
     of
    -1.09
     problems
    -1.06
    ็จ
    -1.05
    ଓ
    -1.04
    ála
    -1.02
     its
    -1.00
    POSITIVE LOGITS
     everyone
    1.55
     everybody
    1.45
    everybody
    1.31
    everyone
    1.22
     Everybody
    1.21
     EVERYONE
    1.21
    hability
    1.21
     Stay
    1.20
     safe
    1.20
    ıyorum
    1.18
    Activations Density 0.011%

    No Known Activations