© 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. 4769
    Prev
    Next
    INDEX
    Explanations

    give to students

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

    phrasal verbs and outcomes

    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
     hinzuf
    0.33
     ಅನ್ನು
    0.29
    ខ្ញ
    0.29
    )}{
    0.28
     Şimdi
    0.28
     genommen
    0.28
     হঠাৎ
    0.28
     angezeigt
    0.28
    itriangular
    0.28
     waarvan
    0.28
    POSITIVE LOGITS
     “
    0.33
     the
    0.28
    il
    0.27
      
    0.26
     more
    0.26
     their
    0.26
    i
    0.25
     ‘
    0.24
    iya
    0.24
     us
    0.24
    Activations Density 1.158%

    No Known Activations