© 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-16K
    7. 11760
    Prev
    Next
    INDEX
    Explanations

    database backups and technical terms

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

    sql database operations

    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
     rosette
    0.53
    PropertySheets
    0.45
    萆
    0.43
    ี
    0.42
    wpilib
    0.41
     Jayne
    0.40
    Sandy
    0.40
    TabView
    0.40
    Styled
    0.39
    ViewModel
    0.38
    POSITIVE LOGITS
    antlr
    0.50
    postgresql
    0.47
    ８
    0.46
    ９
    0.46
    पर्स
    0.45
     கடுமையான
    0.45
    noDB
    0.44
    uncio
    0.44
    ocommit
    0.44
    shint
    0.44
    Activations Density 0.010%

    No Known Activations