© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13116
    Prev
    Next
    INDEX
    Explanations

    breaking free of restrictions

    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_13_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
    endy
    1.24
    NORTH
    1.12
    proper
    1.11
     anyway
    1.09
    proliferation
    1.08
    databind
    1.07
    여기
    1.07
    SOUTH
    1.06
    ✗
    1.06
    我不
    1.06
    POSITIVE LOGITS
     tokoh
    1.06
     akan
    0.99
     membentuk
    0.97
     mengikuti
    0.97
     menjadi
    0.97
     bohater
    0.97
     menciptakan
    0.97
     meraih
    0.96
    係る
    0.95
     otrzym
    0.93
    Activations Density 0.055%

    No Known Activations