© 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. 132444
    Prev
    Next
    INDEX
    Explanations

    completely , straps . agencies working

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

    time-based learning plans

    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
     verhindert
    0.48
    zentrum
    0.45
     çünkü
    0.45
     mencionar
    0.44
     estuv
    0.43
    ◯
    0.43
     ಕ್ಯಾ
    0.43
     સ્ટ
    0.42
     rilev
    0.42
     کنگ
    0.42
    POSITIVE LOGITS
     freehold
    0.49
    ల్లి
    0.48
    ',
    0.47
     Wolverhampton
    0.46
     the
    0.44
     Offset
    0.44
     lease
    0.43
    则
    0.43
    слова
    0.43
    旨
    0.43
    Activations Density 0.002%

    No Known Activations