© 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. 153037
    Prev
    Next
    INDEX
    Explanations

    next step

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

    text classification and categorization

    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
     DirectX
    0.53
    ⚋
    0.51
    Ком
    0.49
    薅
    0.49
    пен
    0.48
    ociaż
    0.48
    スペ
    0.48
     ईरानी
    0.48
    ξι
    0.48
    плата
    0.47
    POSITIVE LOGITS
    ujj
    0.45
     Students
    0.43
    mvc
    0.43
     furnishes
    0.42
     selam
    0.42
     Plant
    0.42
     fals
    0.42
    csv
    0.41
     )
    0.41
     Minutes
    0.41
    Activations Density 0.000%

    No Known Activations