© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13396
    Prev
    Next
    INDEX
    Explanations

    select * from

    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
    専
    1.29
    独
    1.22
    Summit
    1.16
    テープ
    1.14
    ψε
    1.13
    と呼ばれる
    1.12
    Squ
    1.12
    Graphs
    1.12
    с
    1.11
    Per
    1.11
    POSITIVE LOGITS
     KIA
    1.79
     POLITICAL
    1.75
     FORD
    1.71
     Jeep
    1.71
     VEH
    1.71
     Còn
    1.67
     YEAR
    1.65
     년
    1.64
     Buick
    1.64
     자동차
    1.64
    Activations Density 0.139%

    No Known Activations