© 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. 231864
    Prev
    Next
    INDEX
    Explanations

    specific dates or 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_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
    wyczaj
    0.52
     сх
    0.51
     خورد
    0.50
     आस्ट्रेलिया
    0.48
     प्रिज्म
    0.47
     aguj
    0.46
    remarkable
    0.46
    秤
    0.45
    schemas
    0.45
     esquema
    0.45
    POSITIVE LOGITS
     Panels
    0.52
     departments
    0.47
     Keane
    0.47
     Countess
    0.46
     Departments
    0.46
     Keene
    0.45
    Departments
    0.45
     Panel
    0.44
     Forests
    0.44
     Kitchen
    0.44
    Activations Density 0.000%

    No Known Activations