© 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. 191236
    Prev
    Next
    INDEX
    Explanations

    announcing importance classifications

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

    measuring and quantifying things

    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
    ام
    0.51
    ৯
    0.47
    ون
    0.47
    ्ल
    0.46
    ণ
    0.45
    ات
    0.45
    ت
    0.44
    ים
    0.44
    ة
    0.44
    מ
    0.44
    POSITIVE LOGITS
     proclam
    0.52
     behaupt
    0.50
     році
    0.49
     പ്രച
    0.49
     Frobenius
    0.48
     Biden
    0.47
     famiglie
    0.47
     Session
    0.47
     Window
    0.47
     Familien
    0.47
    Activations Density 0.000%

    No Known Activations