© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74387
    Prev
    Next
    INDEX
    Explanations

    googleapis.com urls

    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
    );
    -2.34
     dopo
    -2.28
    стойчи
    -2.14
     为
    -2.11
    尤其
    -2.08
    礻
    -1.98
     have
    -1.98
    .$,
    -1.98
    基本的に
    -1.97
    𖤣
    -1.97
    POSITIVE LOGITS
    Зно
    2.89
    </h3>
    2.73
    ”،
    2.64
    llavero
    2.38
     saveiro
    2.31
     休閒
    2.27
    鱨
    2.27
     anhänger
    2.27
    </strong>
    2.22
     ſch
    2.20
    Activations Density 0.005%

    No Known Activations