© 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. 141411
    Prev
    Next
    INDEX
    Explanations

    ownership succession or division

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

    hand after

    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
    능
    0.51
    讥
    0.47
     adlı
    0.46
     loài
    0.46
     confusión
    0.46
     woodland
    0.46
     விருப்ப
    0.45
    랑
    0.44
    哴
    0.44
    ınd
    0.44
    POSITIVE LOGITS
     voids
    0.48
     eliminates
    0.45
     fared
    0.44
     deadlines
    0.43
    zero
    0.43
     necessitated
    0.43
    yield
    0.42
    তীর্থ
    0.42
     yields
    0.41
     trims
    0.41
    Activations Density 0.001%

    No Known Activations