© 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. 174926
    Prev
    Next
    INDEX
    Explanations

    diverse origins and types

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

    multi-lingual descriptions and classifications

    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
     androgen
    0.40
     apprenticeship
    0.40
    ↵
    0.39
    MAT
    0.39
     развед
    0.39
     Methods
    0.38
     Apprentices
    0.38
    г
    0.38
    🔬
    0.38
    농
    0.38
    POSITIVE LOGITS
     विविध
    0.57
     exquisite
    0.51
     wundersch
    0.51
     وهذا
    0.50
    ですので
    0.49
     இருப்பதால்
    0.49
     perceiving
    0.48
     ampio
    0.47
     ospiti
    0.47
     conveying
    0.46
    Activations Density 0.002%

    No Known Activations