© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58061
    Prev
    Next
    INDEX
    Explanations

    software defender and public defender

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on occurrences of the word “Defender” (e.g. in titles like “Public Defender,” “Federal Defender,” etc.).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    росло
    -2.73
     rivales
    -2.58
     paraly
    -2.41
    </u>
    -2.36
    nambuco
    -2.34
     使っ
    -2.33
     flaw
    -2.27
    </code>
    -2.27
    menea
    -2.25
     otros
    -2.17
    POSITIVE LOGITS
    ’
    2.58
    ’,
    2.45
     Polícia
    2.33
     nowa
    2.30
    Ꭳ
    2.28
    ’.
    2.25
    蛩
    2.25
     goku
    2.25
    </h2>
    2.22
    衎
    2.20
    Activations Density 0.004%

    No Known Activations