© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1620
    Prev
    Next
    INDEX
    Explanations

    learned from large data

    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_13_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
     notwithstanding
    1.21
    /(
    1.20
     (=
    1.18
     ("
    1.15
     surcharge
    1.14
     (
    1.14
     nond
    1.12
     /
    1.11
     (#
    1.11
     (†
    1.10
    POSITIVE LOGITS
     المشروع
    1.32
     실험
    1.27
    CRUD
    1.23
    Github
    1.23
     프로젝트
    1.21
     pengelolaan
    1.20
    プロジェクト
    1.20
     ฝึก
    1.17
    стики
    1.15
    人類
    1.15
    Activations Density 0.221%

    No Known Activations