© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 749
    Prev
    Next
    INDEX
    Explanations

    fun and

    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_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    is
    1.66
    o
    1.53
    t
    1.52
     by
    1.52
    el
    1.51
    a
    1.49
    ing
    1.48
    z
    1.46
    e
    1.44
    was
    1.40
    POSITIVE LOGITS
    เป็น
    1.15
     préférable
    1.14
     υψη
    1.09
    จะ
    1.06
     ότι
    1.06
     οπο
    1.06
     дов
    1.06
     ισ
    1.05
     εγκα
    1.04
     ανα
    1.03
    Activations Density 2.227%

    No Known Activations