© 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. 2674
    Prev
    Next
    INDEX
    Explanations

    one that

    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
    t
    2.65
    tan
    2.62
    sol
    2.57
    tas
    2.44
    ti
    2.39
    탕
    2.39
    tok
    2.39
    alış
    2.31
    ყოფ
    2.31
    ella
    2.25
    POSITIVE LOGITS
     څر
    2.72
     defaultstate
    2.63
    ফটেন
    2.59
    /−
    2.51
    न्द्रीय
    2.49
    кті
    2.41
    inhib
    2.39
     colleg
    2.37
    SourceIP
    2.36
     چیر
    2.35
    Activations Density 0.194%

    No Known Activations