© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24636
    Prev
    Next
    INDEX
    Explanations

    referencing the past

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    previous
    0.44
    FAQ
    0.38
    posterior
    0.38
    뻔
    0.38
    hr
    0.36
     précédent
    0.36
     précédente
    0.36
     и
    0.35
    τος
    0.35
    МА
    0.35
    POSITIVE LOGITS
     allá
    0.45
     dalam
    0.45
     në
    0.43
     gäller
    0.43
     back
    0.43
     katika
    0.43
     hometown
    0.42
     çap
    0.41
     ży
    0.41
    \...
    0.41
    Activations Density 0.002%

    No Known Activations