© 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. 13-GEMMASCOPE-2-RES-65K
    4. 1253
    Prev
    Next
    INDEX
    Explanations

    "schützen soll" and "Guerra en"

    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_65k_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
    Og
    1.63
    igt
    1.62
    varphi
    1.43
    conform
    1.42
    sub
    1.41
    ޕ
    1.41
    代表
    1.40
    拠
    1.39
     unitary
    1.38
     phonon
    1.37
    POSITIVE LOGITS
     Вели
    1.60
     ammunition
    1.49
    త్రిక
    1.41
     цен
    1.38
     ماده
    1.36
    ریل
    1.34
     Allies
    1.34
     মুক্তিবাহিনীর
    1.32
    ляться
    1.31
     مواد
    1.31
    Activations Density 0.000%

    No Known Activations