© 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. 216096
    Prev
    Next
    INDEX
    Explanations

    president, syndicated, talents, required, judgment

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

    scrambled eggs

    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
    Negative Logits
     Brahma
    0.41
    畜
    0.41
    ne
    0.41
     Bracken
    0.40
    bbe
    0.40
    Him
    0.40
     Naz
    0.40
    hum
    0.39
    him
    0.39
    🟦
    0.39
    POSITIVE LOGITS
    )).
    0.51
     eigent
    0.49
     è
    0.48
    도
    0.48
    ството
    0.47
     automobil
    0.47
     eurozone
    0.46
     godt
    0.45
    leitung
    0.45
     compon
    0.44
    Activations Density 0.000%

    No Known Activations