© 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. 150064
    Prev
    Next
    INDEX
    Explanations

    given such as

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

    problem, character, client, phrase, string, concepts

    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
    understood
    0.52
    ontaneous
    0.51
    asmuch
    0.50
     discontent
    0.49
    valued
    0.49
    兌
    0.48
    living
    0.48
    ientôt
    0.47
    spicuous
    0.47
    兑
    0.47
    POSITIVE LOGITS
     CCN
    0.54
     CFS
    0.52
    مث
    0.50
     KNN
    0.50
     SAS
    0.47
     URI
    0.46
     DAT
    0.46
     ANS
    0.46
     EBS
    0.46
     clinics
    0.45
    Activations Density 0.001%

    No Known Activations