© 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. 86528
    Prev
    Next
    INDEX
    Explanations

    region and language identification

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

    search, service, GPT, current, executed, ForContext

    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
    的
    0.55
     Lines
    0.49
     six
    0.48
    b
    0.47
     Equations
    0.46
     Converse
    0.44
    otid
    0.44
    算
    0.43
     Flaxman
    0.43
    оне
    0.42
    POSITIVE LOGITS
     অঞ্চলে
    0.52
     amminist
    0.52
     região
    0.52
     étrangers
    0.51
     árboles
    0.50
     árvore
    0.50
     regiões
    0.49
     llegue
    0.48
     conoz
    0.47
     byen
    0.47
    Activations Density 0.002%

    No Known Activations