© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108717
    Prev
    Next
    INDEX
    Explanations

    ATP energy phosphorylation

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

    biochemical terms related to ATP (adenosine triphosphate) and energy metabolism in scientific 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_34/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
    лец
    -0.71
    inerea
    -0.69
     Trustee
    -0.66
    titute
    -0.66
     influencia
    -0.65
    Бахар
    -0.65
     deportivas
    -0.65
    entiel
    -0.64
    akar
    -0.63
     GHG
    -0.63
    POSITIVE LOGITS
     ATP
    2.47
    ATP
    2.03
     adenosine
    1.66
     ADP
    1.50
     Aden
    1.41
    ADP
    1.34
    Aden
    1.30
     aden
    1.28
     energy
    1.22
     nucleotide
    1.21
    Activations Density 0.142%

    No Known Activations