© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9455
    Prev
    Next
    INDEX
    Explanations

    marine sponge

    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_22_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
     
    1.91
     】
    1.45
     ▲
    1.43
     \$
    1.39
    。【
    1.38
     !\
    1.37
    
    1.36
     【
    1.33
    \
    1.33
     \\
    1.33
    POSITIVE LOGITS
    <i>
    4.33
    <em>
    4.14
    <code>
    2.09
    <u>
    1.74
    <sub>
    1.73
    <sup>
    1.37
    《
    1.33
    <s>
    1.30
    <unused2140>
    1.17
    ্‌
    1.15
    Activations Density 0.200%

    No Known Activations