© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11947
    Prev
    Next
    INDEX
    Explanations

    He knew

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ppen
    2.00
    irmek
    1.95
    isah
    1.89
    폐
    1.79
    udah
    1.78
    ije
    1.72
    ."],
    1.70
    нием
    1.70
     例文帳に追加
    1.69
    ittää
    1.68
    POSITIVE LOGITS
    𝑡
    2.48
    𝒕
    2.38
    觥
    2.38
    ાર
    2.33
     फीसदी
    2.28
     русский
    2.27
    ետ
    2.26
    ාව
    2.23
     πολυ
    2.19
     centerX
    2.19
    Activations Density 0.004%

    No Known Activations