© 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. 228553
    Prev
    Next
    INDEX
    Explanations

    truth, supplement, model, world, tragedy, play, often

    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
     მიმო
    0.56
    sekut
    0.51
    oriented
    0.50
    abdominal
    0.48
     dihasilkan
    0.48
     फर
    0.47
     मलेशिया
    0.46
    瞅
    0.46
     Developed
    0.46
    rapping
    0.46
    POSITIVE LOGITS
    ↵
    0.48
     squadre
    0.47
     calcite
    0.46
     Oda
    0.46
     onRouteChange
    0.44
    ();
    0.44
     state
    0.44
     conveyance
    0.44
     rgba
    0.43
     adjour
    0.43
    Activations Density 0.001%

    No Known Activations