© 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. 34-GEMMASCOPE-RES-131K
    4. 106547
    Prev
    Next
    INDEX
    Explanations

    court and state jurisdictions

    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_34/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
     Throughout
    -1.34
     penerima
    -1.34
    ябрь
    -1.30
     Trá
    -1.26
    дизайн
    -1.24
     Descub
    -1.20
    besondere
    -1.17
    türk
    -1.17
    etcd
    -1.17
     awalnya
    -1.13
    POSITIVE LOGITS
     -
    1.45
    ()}
    1.45
    </i>
    1.41
    THE
    1.40
    </strong>
    1.34
    )}
    1.30
    ]
    1.29
    んでる
    1.28
    </em>
    1.27
    ))}
    1.26
    Activations Density 0.008%

    No Known Activations