© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15874
    Prev
    Next
    INDEX
    Explanations

    housekeeping and coffee

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

    vulnerability disclosure, recipes, and states

    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_16k_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
     desal
    0.47
    ♻
    0.46
    operateur
    0.45
    чку
    0.45
    algebras
    0.43
     deaminase
    0.42
    人材
    0.42
    arete
    0.42
     bilayers
    0.42
    чке
    0.41
    POSITIVE LOGITS
     I
    0.49
     tenders
    0.47
     tendered
    0.46
     জানিয়েছিলেন
    0.46
     NHS
    0.46
     Statements
    0.46
     Jane
    0.45
     Kazakh
    0.45
     DAW
    0.45
     School
    0.44
    Activations Density 0.004%

    No Known Activations