© 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. 76956
    Prev
    Next
    INDEX
    Explanations

    DRG diagnosis allocation estimation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Rie
    -0.77
     deja
    -0.70
    SPJ
    -0.70
    MatIconModule
    -0.68
    owie
    -0.68
     toco
    -0.67
    霓
    -0.67
    ging
    -0.67
    лек
    -0.66
    rasa
    -0.66
    POSITIVE LOGITS
     overhead
    1.49
     indirect
    1.33
    Indirect
    1.26
     Overhead
    1.24
    overhead
    1.24
    Overhead
    1.23
    driver
    1.14
     driver
    1.09
     Indirect
    1.09
     allocation
    1.05
    Activations Density 0.014%

    No Known Activations