© 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. 193084
    Prev
    Next
    INDEX
    Explanations

    contractual or legal contexts

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

    most likely

    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
     recovery
    0.48
     Throw
    0.47
     Crossing
    0.45
    ↵
    0.44
     del
    0.44
     throw
    0.43
     recover
    0.43
    인데요
    0.43
     decode
    0.42
     module
    0.41
    POSITIVE LOGITS
    드를
    0.57
    ἢ
    0.53
    𒋢
    0.52
    스를
    0.49
    ೪
    0.49
    ಂಜ
    0.48
    트에
    0.48
    ższej
    0.47
    지와
    0.47
    ᴙ
    0.47
    Activations Density 0.000%

    No Known Activations