© 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. 10346
    Prev
    Next
    INDEX
    Explanations

    PowerPoint files and code

    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
    sma
    3.14
    s
    3.04
    houette
    2.81
    タリー
    2.75
    tin
    2.70
    ]("
    2.69
     chloride
    2.64
    ০
    2.64
     GUIDATA
    2.63
    tj
    2.61
    POSITIVE LOGITS
    算了
    2.54
    ھی
    2.48
    ளுடைய
    2.40
    ூட
    2.37
    록
    2.37
    $/../../../../
    2.37
    পালা
    2.35
    اف
    2.29
    rap
    2.26
    وغ
    2.26
    Activations Density 0.008%

    No Known Activations