© 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. 11843
    Prev
    Next
    INDEX
    Explanations

    connect to

    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
    ğı
    2.53
     zewnętrzne
    2.47
    𝚕
    2.46
    \]
    2.26
    ং
    2.24
    ﮨ
    2.19
    ード
    2.19
    seits
    2.18
    英語版
    2.17
    "},{"
    2.16
    POSITIVE LOGITS
    s
    3.58
    т
    3.46
    sion
    3.31
    u
    3.27
    ו
    3.17
    sell
    3.00
    ා
    3.00
    uously
    2.97
    нский
    2.94
    ske
    2.92
    Activations Density 0.056%

    No Known Activations