© 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. 9865
    Prev
    Next
    INDEX
    Explanations

    try catch code

    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
    !:
    1.20
     Brenner
    1.19
    -/
    1.18
    ?/
    1.18
    +/
    1.10
     NCS
    1.07
    ostock
    1.06
     Hove
    1.05
     Mina
    1.05
    :/
    1.04
    POSITIVE LOGITS
    <0x0D>
    2.34
    </h2>
    1.77
    ‬
    1.58
    </th>
    1.55
    </h5>
    1.39
    </a>
    1.26
     \\
    1.24
    </u>
    1.21
    』
    1.16
    ‌.
    1.15
    Activations Density 0.029%

    No Known Activations