© 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. 74757
    Prev
    Next
    INDEX
    Explanations

    reservations essential

    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
    ürdig
    0.49
    ोरेशन
    0.49
     rebell
    0.48
    jenkins
    0.48
     sofas
    0.48
     caoutch
    0.47
    硙
    0.47
     coff
    0.47
    arakhand
    0.46
    क्रेट
    0.46
    POSITIVE LOGITS
     Mn
    0.48
     flowering
    0.48
     unsuitable
    0.44
    MnO
    0.44
    ła
    0.44
     Blüten
    0.44
    2
    0.44
     non
    0.42
     cnt
    0.42
     innych
    0.42
    Activations Density 0.001%

    No Known Activations