© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 29970
    Prev
    Next
    INDEX
    Explanations

    Supreme Court of United States, Victoria, Shia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    凿
    -0.79
     vale
    -0.79
     ense
    -0.78
    masti
    -0.74
    鑿
    -0.73
     plutôt
    -0.73
    posto
    -0.72
    +}$
    -0.71
    ា
    -0.71
     STATEMENT
    -0.70
    POSITIVE LOGITS
    livé
    0.84
     gekennzeichnet
    0.81
     odby
    0.81
     événements
    0.79
    малар
    0.78
     oznac
    0.77
    MERS
    0.76
    mors
    0.75
    žený
    0.75
     peculiarly
    0.75
    Activations Density 0.076%

    No Known Activations