© 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. 10164
    Prev
    Next
    INDEX
    Explanations

    knock-knock jokes and reverse prompts

    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
     Tears
    2.10
    伍
    2.08
     加
    2.03
     लगाना
    2.02
    াম
    2.01
    alama
    1.98
    加
    1.97
    ewarm
    1.97
     দাঁড়
    1.97
    娘
    1.91
    POSITIVE LOGITS
    Composition
    2.11
    Payout
    2.03
     létre
    1.86
    composition
    1.86
    AKS
    1.85
    sap
    1.85
    NewLine
    1.84
    Esc
    1.82
    ਹੀਂ
    1.82
     gens
    1.82
    Activations Density 0.001%

    No Known Activations