© 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. 246190
    Prev
    Next
    INDEX
    Explanations

    above from Upcountry

    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
    MARKED
    0.50
     عندها
    0.49
     emis
    0.49
     empezar
    0.48
     atacar
    0.48
     அப
    0.46
    Departamento
    0.46
    
    0.45
     Мари
    0.45
     desempe
    0.43
    POSITIVE LOGITS
     November
    0.46
     May
    0.45
     Does
    0.44
     September
    0.44
     Cross
    0.44
     October
    0.43
     is
    0.43
     does
    0.43
    자를
    0.43
    ется
    0.42
    Activations Density 0.001%

    No Known Activations