© 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. 36015
    Prev
    Next
    INDEX
    Explanations

    multilingual and formatted text

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

    tables and data structures

    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
    sadpoetry
    0.47
     pérd
    0.43
    ConfigRequest
    0.43
    मपुर
    0.39
    Ky
    0.38
    പ്പെടുന്ന
    0.37
    閁
    0.37
     mainten
    0.37
    別
    0.37
     activ
    0.36
    POSITIVE LOGITS
    ுகளில்
    0.43
     Snake
    0.42
     הזה
    0.40
     lassen
    0.39
    এশিয়া
    0.39
     Signific
    0.38
     دہ
    0.38
     Pew
    0.38
     reproduce
    0.38
     голу
    0.37
    Activations Density 0.000%

    No Known Activations