© 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. 173452
    Prev
    Next
    INDEX
    Explanations

    download for Windows

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

    to + verb/noun

    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
     животных
    0.54
     animali
    0.46
    ฮ
    0.44
    ຊີ
    0.43
     Лу
    0.42
     animales
    0.42
    цаў
    0.42
    Closest
    0.42
    ឋ
    0.42
    ᴸ
    0.41
    POSITIVE LOGITS
     azonban
    0.46
     управ
    0.45
     entanto
    0.45
    但是我
    0.45
    adh
    0.45
     অবশ্য
    0.45
     उमेदवार
    0.44
     اور
    0.44
     اح
    0.43
     Quais
    0.43
    Activations Density 0.001%

    No Known Activations