© 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. 31-GEMMASCOPE-2-RES-262K
    7. 226394
    Prev
    Next
    INDEX
    Explanations

    IMPORTANT

    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
    ×
    0.48
    ught
    0.44
     hel
    0.43
     World
    0.43
     hydrolysis
    0.43
     rescue
    0.43
     resuscitation
    0.43
     मरम्मत
    0.42
    res
    0.41
     tennis
    0.41
    POSITIVE LOGITS
     IMPORTANT
    0.51
    vať
    0.46
     mellett
    0.45
    čin
    0.44
    扎
    0.44
     wichtig
    0.43
    ্যান্ড
    0.42
    féle
    0.42
    ábbi
    0.41
     WaitFor
    0.41
    Activations Density 0.001%

    No Known Activations