© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3150
    Prev
    Next
    INDEX
    Explanations

    happy to announce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     crucial
    1.70
     variables
    1.62
    setInt
    1.53
     effectiveness
    1.52
     problematic
    1.52
     major
    1.50
     critically
    1.49
    霾
    1.47
    setString
    1.47
    onavir
    1.47
    POSITIVE LOGITS
    ereich
    1.72
    بلغ
    1.69
    ทราบ
    1.63
    得知
    1.60
    shire
    1.58
    Lorem
    1.56
     Proud
    1.56
    尝
    1.55
    deh
    1.54
    γγελ
    1.52
    Activations Density 0.144%

    No Known Activations