© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112472
    Prev
    Next
    INDEX
    Explanations

    FBI investigations, arrests, and leadership

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Not in Any Lists

    No Comments

    Negative Logits
    </td>
    -2.48
    </h2>
    -2.45
    ൎ
    -2.44
    </sup>
    -2.22
    匍
    -2.14
    。】
    -2.13
    
    -2.09
    ⼀
    -2.08
    杙
    -2.06
    了解更多
    -2.03
    POSITIVE LOGITS
    zelfde
    2.28
    ↵
    2.20
     sportowe
    2.17
    ’
    2.14
     ";
    
    2.14
    猡
    2.13
    ти
    2.13
     komplette
    2.09
    .
    2.09
    </strong>
    2.05
    Activations Density 0.004%

    No Known Activations