© 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. 7345
    Prev
    Next
    INDEX
    Explanations

    foreign / financial / numbering sequences

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

    for or about

    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
     Lina
    0.39
     Computer
    0.38
     Barker
    0.38
    颢
    0.37
    Computer
    0.36
     Yal
    0.36
    jala
    0.36
     l
    0.36
    Ihr
    0.36
    Tic
    0.36
    POSITIVE LOGITS
     annuel
    0.48
     teljesen
    0.45
    毫不
    0.43
    िफाई
    0.43
    स्फी
    0.43
     cualquier
    0.42
     digress
    0.42
     potpuno
    0.42
     semuanya
    0.42
     indiv
    0.42
    Activations Density 0.001%

    No Known Activations