© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5909
    Prev
    Next
    INDEX
    Explanations

    future, hope, or silence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    </strong>
    4.92
    </em>
    3.60
    </u>
    3.58
    </b>
    3.36
    </i>
    2.27
    </s>
    2.26
    </sup>
    2.22
    </span>
    2.17
    </sub>
    2.08
    </h5>
    2.03
    POSITIVE LOGITS
    ↵↵
    3.33
    .\"
    3.00
    ,\"
    2.98
     \...
    2.98
    \...
    2.80
    \".
    2.66
    \",
    2.63
     阅读全文
    2.48
    \"
    2.42
    )\\
    2.40
    Activations Density 1.461%

    No Known Activations