© 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. 28578
    Prev
    Next
    INDEX
    Explanations

    Borussia

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

    links or email addresses

    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
     моей
    0.45
    ousse
    0.41
     readFile
    0.41
     Tib
    0.39
     বিভাগ
    0.39
     shew
    0.39
     openai
    0.38
    坵
    0.38
     моём
    0.38
    붉
    0.38
    POSITIVE LOGITS
     ,
    0.59
     ，
    0.50
         
    0.44
     (,
    0.44
     ،
    0.43
     )(
    0.43
    “”
    0.41
     。
    0.40
    RON
    0.40
     는
    0.40
    Activations Density 0.087%

    No Known Activations