© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128598
    Prev
    Next
    INDEX
    Explanations

    chemical extraction and purification

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

    chemical and pharmaceutical compounds or substances used in scientific experiments.

    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
    	
    -1.67
     of
    -1.52
     such
    -1.38
    ;
    -1.37
    //
    -1.31
    						
    -1.27
     including
    -1.27
    L
    -1.26
     получи
    -1.26
     -
    -1.26
    POSITIVE LOGITS
    があるので
    1.67
    がありますが
    1.50
    醍
    1.33
    domada
    1.29
     conserver
    1.24
     знает
    1.24
    Struktur
    1.22
     avenir
    1.20
    踌
    1.20
    についても
    1.19
    Activations Density 0.115%

    No Known Activations