© 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. 153279
    Prev
    Next
    INDEX
    Explanations

    Australian made decisions

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

    medical diagnosis

    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
     fertilization
    0.57
     vzduchu
    0.43
     neutralized
    0.43
     subsided
    0.42
    </em>
    0.42
     Residences
    0.42
    exposition
    0.41
     fertil
    0.41
    grams
    0.41
     importantly
    0.41
    POSITIVE LOGITS
    🧛
    0.52
    াকী
    0.51
    Ц
    0.50
    RENT
    0.49
    June
    0.48
    ES
    0.48
    ил
    0.48
    Ад
    0.47
    Reed
    0.47
    讫
    0.47
    Activations Density 0.000%

    No Known Activations