© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6974
    Prev
    Next
    INDEX
    Explanations

    asking for context

    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
    諸
    1.29
    룩
    1.20
    >(&
    1.18
    ructural
    1.16
    xcsche
    1.16
     PUBLICATIONS
    1.16
    GetLastError
    1.15
    电子邮件
    1.15
    Ṛ
    1.14
     रत्
    1.14
    POSITIVE LOGITS
     Normalmente
    0.94
    Different
    0.91
     normalmente
    0.91
     Different
    0.90
     desert
    0.90
     vui
    0.90
     initially
    0.90
     normale
    0.87
     different
    0.86
     изначально
    0.86
    Activations Density 0.227%

    No Known Activations