© 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. 12906
    Prev
    Next
    INDEX
    Explanations

    reward shaping and hacking

    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
    𝐲
    2.06
    𝐛
    2.05
    𝐚
    1.93
    𝐦
    1.93
    𝐨
    1.88
    gäng
    1.88
    .\"
    1.87
     Taxation
    1.85
    𝐢
    1.84
    <0x0C>
    1.81
    POSITIVE LOGITS
    锢
    2.29
    ٰ
    1.64
    傕
    1.58
    ishing
    1.57
    ishment
    1.56
    isco
    1.54
    щено
    1.54
    UARY
    1.50
    ípios
    1.48
    iž
    1.47
    Activations Density 0.202%

    No Known Activations