© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54787
    Prev
    Next
    INDEX
    Explanations

    cytotoxicity, ncbi, chromatography, PMID, ligands

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

    ergonomics and physical demands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ঝে
    0.57
    逡
    0.50
    翛
    0.48
    訾
    0.47
    嚧
    0.47
    ступа
    0.46
    мили
    0.44
     ประจํา
    0.44
     बेंगल
    0.44
    燡
    0.44
    POSITIVE LOGITS
     cytotoxicity
    0.55
    ncbi
    0.52
     chromatography
    0.50
     PMID
    0.50
     ligands
    0.49
     aldehyde
    0.49
     terpen
    0.49
     peptide
    0.48
     resorption
    0.47
     nicotin
    0.47
    Activations Density 0.006%

    No Known Activations