© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2533
    Prev
    Next
    INDEX
    Explanations

    quite impressed or riding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     citations
    1.82
     photons
    1.79
    இல்
    1.76
     knj
    1.74
     ње
    1.73
    lblCredits
    1.72
    beb
    1.72
     decimals
    1.72
    ﻧ
    1.71
    语句
    1.70
    POSITIVE LOGITS
     northwest
    1.79
    屯
    1.77
    南方
    1.76
     northeast
    1.68
     northeastern
    1.58
     southeast
    1.57
     northwestern
    1.55
     north
    1.51
     recruited
    1.50
     residentes
    1.48
    Activations Density 0.139%

    No Known Activations