© 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. 3913
    Prev
    Next
    INDEX
    Explanations

    introducing different options or variations

    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
    ın
    2.72
    uas
    2.46
    dı
    2.43
    cic
    2.38
     rospy
    2.36
    od
    2.33
    g
    2.30
     gemak
    2.29
    ing
    2.26
    炷
    2.26
    POSITIVE LOGITS
    Oku
    2.84
    োগ্য
    2.82
    picked
    2.63
    сей
    2.53
    藏
    2.43
    %{
    2.42
     reco
    2.42
    lights
    2.40
    ASHI
    2.38
     cloak
    2.37
    Activations Density 0.033%

    No Known Activations