© 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. 102003
    Prev
    Next
    INDEX
    Explanations

    business services and transactions

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

    describes how

    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
     kuin
    0.49
     নিবাস
    0.48
     než
    0.48
     tarihi
    0.43
     giv
    0.42
    ą
    0.42
     menand
    0.41
     byd
    0.41
     amministrat
    0.41
     niż
    0.41
    POSITIVE LOGITS
    Си
    0.49
    velle
    0.46
    梫
    0.45
    حه
    0.44
    clients
    0.44
    Semaphore
    0.44
    蒉
    0.43
    ເຄື່ອງ
    0.43
     enterprising
    0.43
    имо
    0.43
    Activations Density 0.000%

    No Known Activations