© 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. 3351
    Prev
    Next
    INDEX
    Explanations

    attention mechanism and its components

    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
    нга
    3.07
    र
    3.05
    т
    2.87
    iato
    2.87
    ्स
    2.71
    rza
    2.69
    م
    2.67
    んですね
    2.60
    ーション
    2.57
    ا
    2.56
    POSITIVE LOGITS
    ък
    2.52
    したもの
    2.33
    厥
    2.31
    ქვს
    2.29
     üzerinden
    2.25
    forth
    2.23
    ky
    2.14
    atch
    2.12
     içinde
    2.09
    givings
    2.08
    Activations Density 0.051%

    No Known Activations