© 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. 81774
    Prev
    Next
    INDEX
    Explanations

    restorative justice

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

    specific context

    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
     वाजिब
    0.54
    性价比
    0.54
    ાર્
    0.49
     ounces
    0.49
     uważ
    0.47
    𝖗
    0.47
    MSFont
    0.47
     farmac
    0.46
    lej
    0.45
     nồi
    0.45
    POSITIVE LOGITS
     positively
    0.46
    verted
    0.45
    adore
    0.42
    hler
    0.42
    clerotic
    0.42
    에도
    0.41
    an
    0.40
    顽
    0.40
    pas
    0.39
    im
    0.39
    Activations Density 0.000%

    No Known Activations