© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1788
    Prev
    Next
    INDEX
    Explanations

    parts of phrases

    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
    AppDesigner
    2.97
    FileAlignment
    2.75
    ⁦
    2.62
    atás
    2.60
    ую
    2.58
    urium
    2.58
     hatta
    2.51
    ﺜ
    2.50
     yarat
    2.48
     bát
    2.48
    POSITIVE LOGITS
    light
    2.83
    *)(
    2.73
     +:+
    2.68
    lighter
    2.64
    ா
    2.56
    haben
    2.53
    [![
    2.48
    ल
    2.45
     light
    2.43
    passes
    2.35
    Activations Density 0.167%

    No Known Activations