© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 796
    Prev
    Next
    INDEX
    Explanations

    directions, dosage, or states

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

    instructions or directions on how to use a product or apply something.

    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
    corazón
    -1.48
     цвят
    -1.41
    primarily
    -1.39
     fornece
    -1.32
     cewek
    -1.31
    apparently
    -1.30
     píše
    -1.29
    often
    -1.29
    hombre
    -1.28
    continues
    -1.28
    POSITIVE LOGITS
     or
    2.30
     your
    2.05
     our
    1.99
     as
    1.56
     of
    1.43
     like
    1.39
           
    1.38
     yourself
    1.38
        
    1.38
     atau
    1.38
    Activations Density 0.019%

    No Known Activations