© 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. 183017
    Prev
    Next
    INDEX
    Explanations

    Flip Camera, times throughout, articles, Buddha, mobile fact

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

    business topics and terms

    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
    patients
    0.51
    ⼯
    0.48
     تطبيقات
    0.47
    Algorithms
    0.47
     לב
    0.47
     دستیاب
    0.46
    灲
    0.46
    機場
    0.46
    '
    0.46
    Patients
    0.45
    POSITIVE LOGITS
     iterates
    0.52
     interdependence
    0.47
    al
    0.46
     responsibility
    0.46
     blank
    0.44
     DIA
    0.44
     isle
    0.44
     Jehová
    0.44
    з
    0.44
     Blank
    0.43
    Activations Density 0.000%

    No Known Activations