© 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. 31-GEMMASCOPE-2-RES-262K
    7. 135306
    Prev
    Next
    INDEX
    Explanations

    demand, input, yellow

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     мной
    0.48
    știg
    0.46
     यशस्वी
    0.46
    QR
    0.46
    CEED
    0.45
     úspě
    0.45
     있
    0.45
    罰
    0.43
     го
    0.42
     男の子
    0.42
    POSITIVE LOGITS
     Bernoulli
    0.46
     Bern
    0.44
     application
    0.44
    肇
    0.43
    炯
    0.43
    ApiClient
    0.42
     Application
    0.41
     constraining
    0.40
     APPLICATION
    0.40
     coeff
    0.40
    Activations Density 0.005%

    No Known Activations