© 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-65K
    7. 2664
    Prev
    Next
    INDEX
    Explanations

    asking for definitions

    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
     hampir
    1.22
     adenos
    1.18
     pouco
    1.17
    즙
    1.13
    ックス
    1.12
    عادة
    1.12
    ترل
    1.11
    無法
    1.11
     рекла
    1.10
    恭
    1.10
    POSITIVE LOGITS
    bez
    0.91
    role
    0.88
     entailed
    0.86
     exactly
    0.86
    oma
    0.83
    ombe
    0.83
     Rolle
    0.82
    opo
    0.82
    why
    0.81
    itched
    0.80
    Activations Density 0.564%

    No Known Activations