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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 15014
    Prev
    Next
    INDEX
    Explanations

    ever used or wondered

    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
    udukan
    2.09
    alist
    2.07
    騫
    1.99
    deque
    1.98
    HideFlags
    1.96
    al
    1.88
     currently
    1.86
    radeon
    1.83
     rectal
    1.82
    acqua
    1.82
    POSITIVE LOGITS
    FromString
    2.24
    ы
    2.14
    ات
    2.10
     <<"
    2.04
    ,\,\
    2.04
    s
    1.99
    rata
    1.93
    َات
    1.90
    sinatra
    1.88
    صبح
    1.85
    Activations Density 0.031%

    No Known Activations