© 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. 84849
    Prev
    Next
    INDEX
    Explanations

    citrate, citric acid, TCA cycle

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

    terminology related to organic acids, particularly citrate and carboxylic acid compounds in biochemical contexts.

    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
     on
    -1.54
     of
    -1.52
     harian
    -1.47
     definitiv
    -1.41
    
    -1.39
    ностях
    -1.38
    estacks
    -1.38
    onsense
    -1.37
    EDING
    -1.34
     direttore
    -1.32
    POSITIVE LOGITS
    でしたが
    1.53
    虯
    1.53
    ஂ
    1.53
    ᠁
    1.46
     endnu
    1.41
    だったが
    1.41
     einzige
    1.39
    </h2>
    1.38
    ılacak
    1.38
     atentos
    1.37
    Activations Density 0.072%

    No Known Activations