© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11073
    Prev
    Next
    INDEX
    Explanations

    describing real implementation requirements

    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
     เรีย
    1.44
     컨
    1.43
     ब्राउन
    1.37
     엄청
    1.37
     весьма
    1.33
     довольно
    1.33
     상당히
    1.32
     khá
    1.31
    퐈
    1.29
     굉장히
    1.28
    POSITIVE LOGITS
     futuras
    1.26
     fairer
    1.22
    安心して
    1.16
    नेटरी
    1.10
     foreseeable
    1.10
    ädig
    1.06
    SPT
    1.06
     easier
    1.06
    utar
    1.06
    忘れ
    1.05
    Activations Density 0.342%

    No Known Activations