© 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. 3972
    Prev
    Next
    INDEX
    Explanations

    looping or cycles

    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
    sstream
    2.88
    thel
    2.44
    tet
    2.43
    סף
    2.43
    th
    2.43
    s
    2.39
    sup
    2.38
    sion
    2.37
    hiana
    2.36
    bringen
    2.34
    POSITIVE LOGITS
    înes
    2.92
    দ্দিক
    2.90
    ၼ်
    2.76
     теря
    2.76
    ܨ
    2.74
    osterone
    2.70
    যথ
    2.69
     convolutions
    2.69
    ິກ
    2.68
    किस्तानी
    2.67
    Activations Density 0.160%

    No Known Activations