© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8009
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
    </sup>
    -1.55
     was
    -1.55
     "";
    -1.38
    蔼
    -1.31
    });
    -1.31
    人也
    -1.24
     แต่
    -1.22
    </h6>
    -1.22
     évidence
    -1.22
    </h2>
    -1.20
    POSITIVE LOGITS
     now
    1.73
     Vainqueur
    1.57
    Other
    1.45
    如今
    1.45
     aktar
    1.44
    不同
    1.41
     felicitación
    1.41
     Meilleures
    1.39
    dür
    1.38
     nourrir
    1.38
    Activations Density 0.015%

    No Known Activations