© 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. 13281
    Prev
    Next
    INDEX
    Explanations

    finance, biology, cloud, legal, physics

    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
     cri
    1.19
     eux
    1.09
     Kano
    1.06
     ケ
    1.05
    oxine
    1.04
     Ã
    1.04
     wrestling
    1.03
    嘰
    1.03
    ürgen
    1.02
     ヘ
    1.02
    POSITIVE LOGITS
    mixin
    1.32
     স্থানে
    1.23
    ási
    1.19
    TINGS
    1.19
    LAYOUT
    1.19
     उजागर
    1.18
    MANAGER
    1.16
    TRACK
    1.14
    gradients
    1.14
    像素
    1.14
    Activations Density 0.001%

    No Known Activations