© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120827
    Prev
    Next
    INDEX
    Explanations

    group by operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     중심으로
    -0.06
     människ
    -0.06
     offsetting
    -0.06
    </table>
    -0.06
    comstock
    -0.06
     meteorite
    -0.06
     را
    -0.06
     outskirts
    -0.06
     risked
    -0.05
    越來越
    -0.05
    POSITIVE LOGITS
    の方法
    0.06
     그냥
    0.06
    就被
    0.06
    ｀)
    0.06
    考试
    0.06
    city
    0.06
     Faj
    0.06
    下面的
    0.06
     just
    0.06
    butadiene
    0.06
    Activations Density 0.004%

    No Known Activations