© 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-16K
    4. 9895
    Prev
    Next
    INDEX
    Explanations

    resource usage and impact

    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
    <start_of_image>
    1.99
    <unused2113>
    1.41
     继续访问
    1.40
    ៏
    1.37
    <0xC2>
    1.35
    <eos>
    1.35
    旳
    1.33
    <h3>
    1.32
    ઞ
    1.31
    ֜
    1.31
    POSITIVE LOGITS
    ↵
    2.21
    </u>
    2.09
    </em>
    2.08
    </i>
    1.98
    </h1>
    1.76
    </span>
    1.47
    </strong>
    1.47
    </b>
    1.34
    </code>
    1.27
    </h2>
    1.19
    Activations Density 0.115%

    No Known Activations