© 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. 147593
    Prev
    Next
    INDEX
    Explanations

    Traveller Systems, AND MET

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

    predicts loan defaults

    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
     permutation
    0.45
    。
    0.45
     erupt
    0.44
     tromb
    0.42
    uit
    0.42
    …
    0.42
     primi
    0.42
     Dime
    0.42
    ，
    0.41
    ouden
    0.41
    POSITIVE LOGITS
     चपेट
    0.46
    ᱕
    0.46
    یث
    0.45
    READER
    0.45
    𝟰
    0.45
    ﹉
    0.45
     сега
    0.44
    stattung
    0.44
    ঞ্চলে
    0.43
    <unused3>
    0.43
    Activations Density 0.000%

    No Known Activations